INDEX

Explanations

questions starting with "What do you think?"

oai_token-act-pair · gpt-3.5-turbo

questions that prompt discussion or opinion seeking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

WAYS

-0.87

ahime

-0.73

boats

-0.70

Interstitial

-0.69

boards

-0.69

mobi

-0.68

thur

-0.67

legram

-0.65

acerb

-0.65

fox

-0.65

POSITIVE LOGITS

 happen

0.80

?]

0.77

omsday

0.72

actic

0.69

iotic

0.66

ederal

0.66

iosyncr

0.65

 notation

0.64

 mean

0.64

?),

0.63

Activations Density 0.051%

questions starting with "What do you think?"

questions that prompt discussion or opinion seeking

No Comments

No Known Activations