INDEX

Explanations

references to legal proceedings and actions

oai_token-act-pair · gpt-3.5-turbo

key terms and phrases associated with authority and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

orks

-0.50

lik

-0.48

Kids

-0.48

edin

-0.48

directory

-0.46

ttp

-0.46

imoto

-0.46

Ð

-0.45

igslist

-0.45

bsite

-0.45

POSITIVE LOGITS

 jaws

0.58

 solemn

0.55

 certainty

0.53

 arra

0.52

 vanquished

0.52

 unquestion

0.51

 majesty

0.51

 Sins

0.49

 JUSTICE

0.49

 courtroom

0.48

Activations Density 1.597%

references to legal proceedings and actions

key terms and phrases associated with authority and accountability

No Comments

No Known Activations