INDEX

Explanations

words related to negative events or controversies

oai_token-act-pair · gpt-3.5-turbo

incidents involving conflict or contentious situations

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

 equivalents

-0.70

 repositories

-0.63

 isEnabled

-0.63

apps

-0.62

optional

-0.59

 poss

-0.59

ographies

-0.58

amina

-0.58

 interchangeable

-0.58

 discretion

-0.57

POSITIVE LOGITS

 involving

0.98

 wherein

0.94

iphany

0.86

 debacle

0.84

 botched

0.82

 earlier

0.79

 rocked

0.77

 conducted

0.77

 sparked

0.77

 last

0.76

Activations Density 0.358%

words related to negative events or controversies

incidents involving conflict or contentious situations

No Comments

No Known Activations