INDEX

Explanations

statements where individuals or entities support or endorse specific plans, projects, or actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating support or backing from influential entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ias

-0.79

bach

-0.79

llor

-0.78

trap

-0.77

hemer

-0.74

perty

-0.73

 largeDownload

-0.72

ulnerability

-0.72

ptoms

-0.71

blems

-0.71

POSITIVE LOGITS

 virtue

0.97

laws

0.82

 afar

0.81

 deed

0.74

 multiplying

0.73

 Voices

0.72

 pledging

0.71

 citing

0.71

 Standing

0.71

 decree

0.70

Activations Density 0.120%

statements where individuals or entities support or endorse specific plans, projects, or actions

phrases indicating support or backing from influential entities

No Comments

No Known Activations