INDEX

Explanations

contractions or possessive forms involving the apostrophe followed by 'in'

oai_token-act-pair · gpt-3.5-turbo

instances of the apostrophe being used in dialogue or contractions

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

irez

-0.81

rendered

-0.79

arer

-0.78

ĻĤ

-0.76

icz

-0.76

uj

-0.76

agos

-0.73

¨

-0.72

ihar

-0.71

¿½

-0.68

POSITIVE LOGITS

 fashioned

0.80

Malley

0.74

eous

0.71

 Bastard

0.68

 Chosen

0.68

WOOD

0.64

 Solitaire

0.64

 Syndrome

0.63

 Plenty

0.63

 Mama

0.62

Activations Density 0.017%

contractions or possessive forms involving the apostrophe followed by 'in'

instances of the apostrophe being used in dialogue or contractions

No Comments

No Known Activations