INDEX

Explanations

phrases related to external entities or influences

oai_token-act-pair · gpt-3.5-turbo

references to external factors or influences

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

EY

-0.81

ander

-0.79

killer

-0.78

birds

-0.78

ony

-0.77

oned

-0.76

SHIP

-0.76

Maker

-0.74

olk

-0.74

KING

-0.72

POSITIVE LOGITS

ities

1.13

ized

0.99

izing

0.93

ization

0.89

izations

0.85

 combustion

0.85

ised

0.81

izable

0.81

izes

0.80

 affairs

0.80

Activations Density 0.028%

phrases related to external entities or influences

references to external factors or influences

No Comments

No Known Activations