INDEX

Explanations

adjectives or adverbs emphasizing the quality or condition of something

oai_token-act-pair · gpt-3.5-turbo

the word "perfectly" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

NetMessage

-0.79

SEE

-0.77

hyde

-0.76

anwhile

-0.74

ulative

-0.72

mere

-0.71

ulton

-0.70

Downloadha

-0.70

jri

-0.69

hao

-0.68

POSITIVE LOGITS

 suited

1.06

 aligned

0.98

 timed

0.85

 positioned

0.82

@@

0.82

 tuned

0.81

 behaved

0.78

fit

0.78

 sized

0.75

 encaps

0.75

Activations Density 0.020%

adjectives or adverbs emphasizing the quality or condition of something

the word "perfectly" in various contexts

No Comments

No Known Activations