INDEX

Explanations

instances where individuals publicly disclose information or accusations

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals coming forward to report experiences or accusations

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

tein

-0.69

rip

-0.66

 Cong

-0.63

Rocket

-0.61

 Boost

-0.59

icion

-0.58

Goo

-0.58

nesota

-0.58

 Sent

-0.58

akings

-0.57

POSITIVE LOGITS

onyms

0.82

 voluntarily

0.78

 allegations

0.77

 testimonies

0.75

 accusations

0.71

ecided

0.70

circle

0.69

osal

0.66

anced

0.65

river

0.65

Activations Density 0.018%

instances where individuals publicly disclose information or accusations

mentions of individuals coming forward to report experiences or accusations

No Comments

No Known Activations