INDEX

Explanations

places or names with prominent capitalization patterns

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to places or significant entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 repl

-0.66

 RELE

-0.66

 constrained

-0.63

 comp

-0.63

 affili

-0.62

 clipboard

-0.62

CLS

-0.60

 medic

-0.60

 substit

-0.60

 reads

-0.60

POSITIVE LOGITS

aga

1.03

eal

0.98

etts

0.97

ois

0.97

vous

0.94

riks

0.94

amiya

0.92

iken

0.92

ilus

0.92

opa

0.91

Activations Density 0.272%

places or names with prominent capitalization patterns

specific names or terms related to places or significant entities

No Comments

No Known Activations