INDEX

Explanations

titles or mentions related to a specific organization or position, likely "General"

oai_token-act-pair · gpt-3.5-turbo

references to "General" as part of titles or names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ï¸

-0.85

gypt

-0.75

bley

-0.73

ologies

-0.71

lihood

-0.66

gger

-0.64

gp

-0.63

nown

-0.63

vana

-0.62

some

-0.61

POSITIVE LOGITS

izations

1.13

isations

0.93

ization

0.92

 Electric

0.88

isation

0.87

idad

0.84

 Dynamics

0.84

 Purpose

0.83

istration

0.82

 Motors

0.81

Activations Density 0.022%

titles or mentions related to a specific organization or position, likely "General"

references to "General" as part of titles or names

No Comments

No Known Activations