INDEX

Explanations

words or phrases indicating obstacles, challenges, or difficulties

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate difficulty or obstacles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Stars

-0.72

Originally

-0.68

!/

-0.67

Introduced

-0.65

 Variant

-0.63

rika

-0.62

roma

-0.62

kind

-0.62

rak

-0.62

mology

-0.59

POSITIVE LOGITS

enged

0.80

aneously

0.75

 prey

0.74

ible

0.73

chain

0.71

ioned

0.68

anced

0.68

untary

0.67

forced

0.66

 enforce

0.65

Activations Density 0.055%

words or phrases indicating obstacles, challenges, or difficulties

phrases that indicate difficulty or obstacles

No Comments

No Known Activations