INDEX

Explanations

phrases where something is judged or assessed

oai_token-act-pair · gpt-3.5-turbo

statements about perceptions or judgments regarding various subjects

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

inas

-0.70

load

-0.66

sheets

-0.66

Ring

-0.65

cies

-0.64

mouth

-0.63

loads

-0.63

brow

-0.61

 Lann

-0.61

adra

-0.59

POSITIVE LOGITS

phas

0.89

 favorably

0.88

 Tradable

0.82

 "$:/

0.77

soDeliveryDate

0.73

é¾įå¥ĳå£«

0.72

iotics

0.71

 considered

0.71

 expend

0.69

 elig

0.66

Activations Density 0.025%

phrases where something is judged or assessed

statements about perceptions or judgments regarding various subjects

No Comments

No Known Activations