INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

references to people, organizations, or entities relevant to political and social discussions

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

allery

-0.76

 Mehran

-0.69

lihood

-0.66

 withd

-0.63

enegger

-0.62

gerald

-0.62

ought

-0.61

OULD

-0.61

"]=>

-0.61

akov

-0.60

POSITIVE LOGITS

 intact

0.73

 impunity

0.68

dding

0.67

 flourish

0.63

 pals

0.63

 linem

0.62

 buddies

0.61

 hindsight

0.61

ello

0.60

 mates

0.60

Activations Density 0.653%

locations or places

references to people, organizations, or entities relevant to political and social discussions

No Comments

No Known Activations