INDEX

Explanations

locations or places indicated by the word 'town'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "of" in various contexts

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

âĹ¼

-0.88

Reviewer

-0.84

 certs

-0.79

-0.76

<?

-0.72

*/(

-0.70

illance

-0.68

wcs

-0.68

uristic

-0.68

WARE

-0.68

POSITIVE LOGITS

Alb

0.85

 Towns

0.85

 Trinidad

0.85

 Brittany

0.81

 southwestern

0.80

Nev

0.80

 Dover

0.79

 Beau

0.79

 Mour

0.79

La

0.78

Activations Density 0.098%

locations or places indicated by the word 'town'

occurrences of the word "of" in various contexts

No Comments

No Known Activations