INDEX

Explanations

phrases indicating placement or positioning of objects or individuals

oai_token-act-pair · gpt-3.5-turbo

words related to placing or positioning objects or items

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

ucci

-0.74

SB

-0.66

hess

-0.64

ery

-0.63

externalActionCode

-0.61

esome

-0.61

eh

-0.60

 erupt

-0.59

straight

-0.58

ilant

-0.58

POSITIVE LOGITS

 bets

1.07

holders

0.98

 emphasis

0.97

holder

0.95

 blame

0.87

 restraints

0.76

ngth

0.76

 moratorium

0.76

 cursor

0.76

 constraints

0.76

Activations Density 0.082%

phrases indicating placement or positioning of objects or individuals

words related to placing or positioning objects or items

No Comments

No Known Activations