INDEX

Explanations

phrases related to privacy policies

oai_token-act-pair · gpt-3.5-turbo

references to privacy policies and notices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.61

 lobb

-0.57

uana

-0.55

 retri

-0.55

 scapego

-0.53

mun

-0.53

 coerc

-0.53

 Turks

-0.51

imates

-0.51

 chuck

-0.51

POSITIVE LOGITS

Privacy

0.62

antha

0.62

 Submit

0.61

 Could

0.61

 Email

0.60

 disclaimer

0.60

php

0.56

ilty

0.55

 Divinity

0.54

 Meter

0.54

Activations Density 0.012%

phrases related to privacy policies

references to privacy policies and notices

No Comments

No Known Activations