INDEX

Explanations

terms indicating disagreements or contradictions between different entities

oai_token-act-pair · gpt-3.5-turbo

terms related to conflict or disagreement between ideas, entities, or situations

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

veland

-0.72

 helicop

-0.72

dark

-0.66

agin

-0.65

cre

-0.64

chat

-0.62

disk

-0.62

anish

-0.62

kn

-0.59

gins

-0.58

POSITIVE LOGITS

 sexes

0.85

 disparate

0.83

SHIP

0.80

 between

0.75

 twins

0.73

 contradictory

0.72

 oppos

0.71

lihood

0.71

 dots

0.70

 halves

0.69

Activations Density 0.100%

terms indicating disagreements or contradictions between different entities

terms related to conflict or disagreement between ideas, entities, or situations

No Comments

No Known Activations