INDEX

Explanations

verbs related to authority or intervention

oai_token-act-pair · gpt-3.5-turbo

words related to interference and violations of rules or principles

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

 Lifetime

-0.62

lik

-0.56

 brackets

-0.56

 trajectory

-0.55

 Cycling

-0.54

 impulse

-0.54

alien

-0.54

hem

-0.54

ulton

-0.53

href

-0.52

POSITIVE LOGITS

rences

0.79

âĸ¬

0.77

 upon

0.74

ulates

0.70

bley

0.70

 peacefully

0.69

kees

0.69

prises

0.66

verning

0.64

 seiz

0.64

Activations Density 0.135%

verbs related to authority or intervention

words related to interference and violations of rules or principles

No Comments

No Known Activations