INDEX

Explanations

words and phrases related to conflicts or disagreements

oai_token-act-pair · gpt-3.5-turbo

words that describe a state of being or a classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

chwitz

-0.76

tumblr

-0.74

 Territory

-0.72

Ô

-0.72

terday

-0.71

¥µ

-0.70

awaru

-0.69

BALL

-0.68

BIP

-0.68

ETH

-0.68

POSITIVE LOGITS

amped

1.12

amps

1.11

ipper

1.10

ojure

1.09

ogged

1.01

uster

0.97

ashing

0.96

inton

0.95

ared

0.92

ippers

0.92

Activations Density 0.008%

words and phrases related to conflicts or disagreements

words that describe a state of being or a classification

No Comments

No Known Activations