INDEX

Explanations

words related to actions that come before or are in front of something

oai_token-act-pair · gpt-3.5-turbo

terms related to linguistic structures and sequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Fair

-0.75

hub

-0.69

RF

-0.69

arov

-0.66

gal

-0.66

fair

-0.65

Hub

-0.63

Hum

-0.63

erm

-0.62

million

-0.62

POSITIVE LOGITS

 preced

1.10

 preceded

1.02

icter

0.93

ebin

0.87

apolis

0.76

 tempted

0.75

etr

0.74

ģĸ

0.72

cules

0.71

ences

0.70

Activations Density 0.009%

words related to actions that come before or are in front of something

terms related to linguistic structures and sequence

No Comments

No Known Activations