INDEX

Explanations

phrases or sentences describing something as ideal or perfect for a particular purpose or situation

oai_token-act-pair · gpt-3.5-turbo

phrases and terms that describe suitability or perfection for specific situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tallied

-0.69

erity

-0.63

urance

-0.62

 halted

-0.62

bands

-0.62

 clipboard

-0.61

roy

-0.61

 inconsist

-0.60

 backlog

-0.60

hes

-0.59

POSITIVE LOGITS

TI

0.79

wcsstore

0.75

isphere

0.74

ovie

0.74

 capitalize

0.71

 compliment

0.70

 encaps

0.70

ãĥ³ãĤ¸

0.69

-+-+

0.67

 complement

0.65

Activations Density 0.146%

phrases or sentences describing something as ideal or perfect for a particular purpose or situation

phrases and terms that describe suitability or perfection for specific situations

No Comments

No Known Activations