INDEX

Explanations

phrases related to enabling or permitting actions or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating enabling or facilitative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

been

-0.72

ask

-0.71

daq

-0.69

ko

-0.68

displayText

-0.66

lean

-0.65

ohm

-0.63

kind

-0.62

worn

-0.62

ãĥĩãĤ£

-0.61

POSITIVE LOGITS

us

1.21

 them

0.91

him

0.85

Reviewer

0.84

me

0.83

 researchers

0.80

 doctors

0.73

 astronomers

0.73

you

0.73

 ample

0.73

Activations Density 0.092%

phrases related to enabling or permitting actions or conditions

phrases indicating enabling or facilitative actions

No Comments

No Known Activations