INDEX

Explanations

words related to conflict or confrontation

oai_token-act-pair · gpt-3.5-turbo

variations of the word "conflict" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 gobl

-0.78

 microw

-0.69

SEN

-0.65

HO

-0.63

ellar

-0.62

 voting

-0.60

electric

-0.58

 vault

-0.58

encer

-0.58

 smart

-0.58

POSITIVE LOGITS

lict

1.33

licts

1.11

liction

1.04

ãĥł

0.81

owship

0.80

unia

0.80

lich

0.79

ually

0.76

nesses

0.75

ãĤ¼

0.73

Activations Density 0.032%

words related to conflict or confrontation

variations of the word "conflict" and related terms

No Comments

No Known Activations