INDEX

Explanations

statements or assertions

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "the fact that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

aukee

-0.77

Si

-0.72

pec

-0.70

vc

-0.69

uttering

-0.66

ocking

-0.64

yn

-0.64

ately

-0.63

Eye

-0.63

wn

-0.63

POSITIVE LOGITS

 someone

0.96

 they

0.94

 nobody

0.87

 there

0.84

 somebody

0.84

 hindsight

0.83

we

0.81

 everyone

0.79

 anyone

0.76

 humans

0.76

Activations Density 0.084%

statements or assertions

instances of the phrase "the fact that."

No Comments

No Known Activations