INDEX

Explanations

words related to names or specific terms

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant names related to people and places

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ĨĴ

-0.81

hovah

-0.74

©¶æ

-0.74

ciples

-0.72

rypted

-0.70

ł

-0.69

heon

-0.68

orea

-0.68

urrency

-0.67

nep

-0.66

POSITIVE LOGITS

cloth

0.87

mand

0.82

zai

0.80

dress

0.79

hur

0.79

pring

0.76

pour

0.76

Downloadha

0.75

oust

0.73

enough

0.72

Activations Density 0.020%

words related to names or specific terms

proper nouns and significant names related to people and places

No Known Activations