INDEX

Explanations

mentions of making a positive impact or difference

oai_token-act-pair · gpt-3.5-turbo

references to making a positive impact or difference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

oked

-0.84

IDES

-0.70

©¶æ

-0.69

cephal

-0.69

stra

-0.69

earchers

-0.68

urat

-0.68

inges

-0.66

 Strauss

-0.64

dden

-0.63

POSITIVE LOGITS

Shape

0.70

EFF

0.67

IAL

0.65

ļéĨĴ

0.64

 whatsoever

0.63

 wherever

0.61

ileaks

0.60

hole

0.60

hift

0.60

Marginal

0.59

Activations Density 0.021%

mentions of making a positive impact or difference

references to making a positive impact or difference

No Comments

No Known Activations