INDEX

Explanations

words related to authority and regulations

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" in various contexts

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

Times

-0.76

WER

-0.71

onga

-0.65

ummer

-0.65

YP

-0.64

MU

-0.62

ADVERTISEMENT

-0.62

Ws

-0.61

usk

-0.61

ãĥķãĤ¡

-0.61

POSITIVE LOGITS

 therefore

1.05

 consequently

0.95

 thus

0.89

 hence

0.89

 secondly

0.82

 then

0.76

 learns

0.75

 participates

0.74

 oversaw

0.73

 collects

0.73

Activations Density 0.564%

words related to authority and regulations

the conjunction "and" in various contexts

No Comments

No Known Activations