INDEX

Explanations

statements related to activities and merits of particular members or users

oai_token-act-pair · gpt-3.5-turbo

metrics related to user activity and membership status

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

eus

-0.93

Bey

-0.73

 Siem

-0.69

Sov

-0.69

FIR

-0.66

 Aram

-0.66

nep

-0.65

cham

-0.65

Atl

-0.65

AAF

-0.64

POSITIVE LOGITS

essions

0.79

Merit

0.79

 Posts

0.78

oster

0.78

votes

0.76

okemon

0.75

swick

0.74

payer

0.73

ategories

0.73

lia

0.71

Activations Density 0.051%

statements related to activities and merits of particular members or users

metrics related to user activity and membership status

No Comments

No Known Activations