INDEX

Explanations

privacy-related phrases or notifications

oai_token-act-pair · gpt-3.5-turbo

terms related to privacy notices and policies

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

 coord

-0.71

pires

-0.68

uana

-0.64

gran

-0.61

erent

-0.61

_>

-0.60

mun

-0.57

olt

-0.56

 Galile

-0.55

Js

-0.55

POSITIVE LOGITS

 disclaimer

0.72

 Newsletter

0.69

 Submit

0.67

Privacy

0.67

antha

0.64

 slip

0.63

 Email

0.63

 curl

0.63

 WRITE

0.62

ificate

0.61

Activations Density 0.014%

privacy-related phrases or notifications

terms related to privacy notices and policies

No Comments

No Known Activations