INDEX

Explanations

instances where the text discusses potential consequences or outcomes

oai_token-act-pair · gpt-3.5-turbo

descriptions of survival and health-related outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 misunderstanding

-0.65

ICO

-0.60

 misunderstand

-0.59

 trolling

-0.56

SEO

-0.55

 Architects

-0.55

 behavi

-0.55

 miscon

-0.55

 Firstly

-0.55

catentry

-0.55

POSITIVE LOGITS

aterasu

0.69

 afterward

0.61

 twice

0.59

kefeller

0.59

 ninety

0.57

 averaged

0.57

 Whitman

0.56

eligible

0.55

 virtually

0.54

bernatorial

0.53

Activations Density 1.474%

instances where the text discusses potential consequences or outcomes

descriptions of survival and health-related outcomes

No Comments

No Known Activations