INDEX

Explanations

phrases related to controversies and scrutiny

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a sequence of events or consequences following certain actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tick

-0.76

psy

-0.75

cin

-0.74

aez

-0.74

Typ

-0.74

 isEnabled

-0.74

minus

-0.74

email

-0.70

Anyway

-0.70

achel

-0.69

POSITIVE LOGITS

 discovering

1.00

 revelations

0.92

 announcing

0.89

 seeing

0.89

 noticing

0.85

 witnessing

0.83

words

0.83

 failing

0.82

noon

0.78

 repeated

0.78

Activations Density 0.104%

phrases related to controversies and scrutiny

phrases indicating a sequence of events or consequences following certain actions

No Comments

No Known Activations