INDEX

Explanations

negative statements or criticisms

oai_token-act-pair · gpt-3.5-turbo

negations and phrases expressing doubt or lack of certainty

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

olon

-0.73

lique

-0.73

cerpt

-0.68

ali

-0.67

ription

-0.66

lesi

-0.65

ourse

-0.65

lav

-0.65

Lux

-0.65

andan

-0.64

POSITIVE LOGITS

 darn

0.80

iga

0.74

IFT

0.68

Cola

0.66

hin

0.64

CO

0.63

Sad

0.62

 divorced

0.62

WHERE

0.62

ifiable

0.62

Activations Density 0.092%

negative statements or criticisms

negations and phrases expressing doubt or lack of certainty

No Comments

No Known Activations