INDEX

Explanations

phrases related to actions or behaviors attributed to specific individuals

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate involvement or responsibility

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

berus

-0.67

 plum

-0.65

 grandchildren

-0.64

 millenn

-0.63

kefeller

-0.62

ricane

-0.62

 pods

-0.62

 basil

-0.59

 Reincarn

-0.59

 broom

-0.59

POSITIVE LOGITS

offs

0.74

uary

0.72

allo

0.66

..................

0.66

 guiActiveUn

0.64

displayText

0.62

aque

0.62

aking

0.61

lab

0.60

meal

0.60

Activations Density 0.014%

phrases related to actions or behaviors attributed to specific individuals

phrases that indicate involvement or responsibility

No Comments

No Known Activations