INDEX

Explanations

phrases related to important or significant historical events or moments

oai_token-act-pair · gpt-3.5-turbo

references to significant historical events or contexts

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

Downloadha

-0.94

nery

-0.90

Flow

-0.78

gans

-0.76

Kids

-0.75

cius

-0.75

cham

-0.73

xia

-0.72

ullah

-0.71

ya

-0.71

POSITIVE LOGITS

 landmark

1.11

 preservation

1.09

 significance

0.98

orically

0.96

istically

0.95

 lows

0.95

 landmarks

0.90

orical

0.86

icity

0.83

 achievement

0.82

Activations Density 0.022%

phrases related to important or significant historical events or moments

references to significant historical events or contexts

No Comments

No Known Activations