INDEX

Explanations

proper nouns, particularly related to organizations, people, and locations

oai_token-act-pair · gpt-3.5-turbo

references to various organizations, groups, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ô

-0.89

peed

-0.78

 Glas

-0.74

ufact

-0.69

é¾įå¥ĳå£«

-0.68

hots

-0.68

Redd

-0.66

icro

-0.66

imeters

-0.65

arious

-0.64

POSITIVE LOGITS

 itself

1.31

 hierarchy

0.94

 logo

0.87

 constitution

0.87

 bureaucracy

0.86

 ecosystem

0.85

 workforce

0.84

 motto

0.83

 treasury

0.83

 homepage

0.79

Activations Density 0.313%

proper nouns, particularly related to organizations, people, and locations

references to various organizations, groups, or entities

No Comments

No Known Activations