INDEX

Explanations

numeric values mentioned in a document

oai_token-act-pair · gpt-3.5-turbo

references to voting and audience engagement metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

gat

-0.78

rums

-0.71

aucas

-0.69

 suprem

-0.69

forth

-0.69

ding

-0.68

ties

-0.66

 scapego

-0.65

 owing

-0.65

spo

-0.62

POSITIVE LOGITS

poons

0.81

 VIEW

0.79

IST

0.78

Reviewed

0.77

 Views

0.76

Ago

0.76

Reply

0.75

 Overall

0.72

 Duration

0.72

ago

0.72

Activations Density 0.113%

numeric values mentioned in a document

references to voting and audience engagement metrics

No Comments

No Known Activations