INDEX

Explanations

words related to tense or risky situations

oai_token-act-pair · gpt-3.5-turbo

phrases that describe the state or condition of a situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Flavoring

-0.98

 Creed

-0.91

 swipe

-0.71

tymology

-0.69

 acknowled

-0.68

thood

-0.66

 inscription

-0.65

 alphabet

-0.64

 swoop

-0.63

 caches

-0.63

POSITIVE LOGITS

 unfavorable

1.14

 conducive

1.10

 favorable

1.10

 dire

1.09

 worsened

1.08

 deteriorating

1.03

 intolerable

1.02

 conditions

0.98

 worsening

0.97

 favourable

0.92

Activations Density 0.242%

words related to tense or risky situations

phrases that describe the state or condition of a situation

No Comments

No Known Activations