INDEX

Explanations

the word 'wide'

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize a broad scope or variety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cair

-0.70

ICAN

-0.66

lda

-0.66

 Maid

-0.64

 Uriel

-0.63

CB

-0.62

ilater

-0.62

act

-0.62

 Patron

-0.61

adobe

-0.61

POSITIVE LOGITS

creen

0.95

leaf

0.94

 wide

0.87

spread

0.86

open

0.84

 scope

0.83

sheets

0.83

 ranging

0.83

 wider

0.81

 breadth

0.81

Activations Density 0.022%

the word 'wide'

phrases that emphasize a broad scope or variety

No Comments

No Known Activations