INDEX

Explanations

proper nouns related to a specific individual or organization

oai_token-act-pair · gpt-3.5-turbo

the mention of specific names or entities related to business or technology

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

Not in Any Lists

No Comments

Negative Logits

vertising

-0.89

itive

-0.88

xtap

-0.77

blind

-0.75

ividual

-0.74

pedia

-0.73

livious

-0.73

glas

-0.70

endum

-0.69

peat

-0.69

POSITIVE LOGITS

 Hert

0.93

atican

0.77

 Morg

0.74

ILA

0.73

ille

0.70

Nav

0.70

 hump

0.69

MET

0.69

Chel

0.69

 Herz

0.68

Activations Density 0.018%

proper nouns related to a specific individual or organization

the mention of specific names or entities related to business or technology

No Comments

No Known Activations