INDEX

Explanations

words ending in '-ially' with a higher activation value

oai_token-act-pair · gpt-3.5-turbo

words and phrases that modify or describe characteristics or attributes

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

href

-0.71

Trend

-0.68

ocene

-0.63

 Chaser

-0.63

ilan

-0.62

 Tribune

-0.62

Nor

-0.62

uras

-0.62

 Franks

-0.62

 Orchestra

-0.62

POSITIVE LOGITS

ially

1.19

 speaking

0.91

mph

0.76

inately

0.74

ename

0.71

 educated

0.71

 avail

0.70

quire

0.70

 extinct

0.69

mares

0.69

Activations Density 0.005%

words ending in '-ially' with a higher activation value

words and phrases that modify or describe characteristics or attributes

No Comments

No Known Activations