INDEX

Explanations

proper nouns related to locations, organizations, and individuals

oai_token-act-pair · gpt-3.5-turbo

terms indicating inclusion or association with groups

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

 Woodward

-0.75

afety

-0.67

 Debor

-0.59

 correction

-0.58

chie

-0.58

uid

-0.58

aturday

-0.56

 shootout

-0.56

PAN

-0.55

zag

-0.55

POSITIVE LOGITS

 respectively

1.43

 combined

0.84

ibaba

0.80

 latter

0.77

 collectively

0.76

Interstitial

0.72

idges

0.72

depending

0.72

together

0.71

 jointly

0.71

Activations Density 0.801%

proper nouns related to locations, organizations, and individuals

terms indicating inclusion or association with groups

No Comments

No Known Activations