INDEX

Explanations

references to upgrades or offers for upgrades

oai_token-act-pair · gpt-3.5-turbo

references to upgrades or enhancements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bered

-0.77

otropic

-0.72

zman

-0.68

LESS

-0.68

 Caption

-0.67

tering

-0.67

pal

-0.67

 Unch

-0.66

SELECT

-0.65

avery

-0.65

POSITIVE LOGITS

grades

0.97

ments

0.96

grading

0.92

 upgrades

0.89

xual

0.84

graded

0.82

mentation

0.82

 upgrade

0.78

IOR

0.72

 upgrading

0.71

Activations Density 0.037%

references to upgrades or offers for upgrades

references to upgrades or enhancements

No Comments

No Known Activations