INDEX

Explanations

specific nouns related to actions or entities

oai_token-act-pair · gpt-3.5-turbo

nouns and terms related to organizational structures or entities

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

sbm

-0.71

anyl

-0.70

é¾įå

-0.65

é»Ĵ

-0.64

ittees

-0.64

mx

-0.63

hots

-0.62

utm

-0.59

cca

-0.57

POSITIVE LOGITS

 itself

1.19

 bench

0.81

's

0.74

 grate

0.74

 logo

0.73

 herself

0.73

mentioned

0.73

 mechanic

0.71

 cutter

0.70

ultimate

0.70

Activations Density 0.483%

specific nouns related to actions or entities

nouns and terms related to organizational structures or entities

No Comments

No Known Activations