INDEX

Explanations

phrases related to various types of influences and concerns

oai_token-act-pair · gpt-3.5-turbo

phrases related to concerns, risks, and statistical data

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yrics

-0.58

ravings

-0.58

arlane

-0.55

ollah

-0.54

 hindsight

-0.53

©¶æ

-0.52

illions

-0.52

ilde

-0.52

ãĤ¦ãĤ¹

-0.52

ãĥ©

-0.51

POSITIVE LOGITS

MSN

0.84

0.79

0.78

 whereas

0.76

 because

0.76

 here

0.74

 besides

0.72

.;

0.71

 although

0.68

 anyways

0.68

Activations Density 0.885%

phrases related to various types of influences and concerns

phrases related to concerns, risks, and statistical data

No Comments

No Known Activations