INDEX

Explanations

news-related phrases and alerts

oai_token-act-pair · gpt-3.5-turbo

recurring mentions of news stories and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lessness

-0.72

fy

-0.67

naires

-0.60

mate

-0.60

lly

-0.56

ties

-0.56

 base

-0.56

 comm

-0.54

 descriptor

-0.54

 symbolism

-0.53

POSITIVE LOGITS

pring

0.83

poons

0.82

everal

0.82

linger

0.80

ource

0.80

ummer

0.80

hel

0.78

aurus

0.78

peed

0.77

uggest

0.77

Activations Density 0.065%

news-related phrases and alerts

recurring mentions of news stories and reports

No Comments

No Known Activations