INDEX

Explanations

proper nouns related to different named entities such as organizations, locations, and individuals

oai_token-act-pair · gpt-3.5-turbo

the special character end-of-text and instances of a specific entity or name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inates

-0.94

uthor

-0.90

IVE

-0.82

£ı

-0.82

abilia

-0.80

URA

-0.79

 Wonderland

-0.77

ãĥĩãĤ£

-0.77

¬¼

-0.77

istant

-0.75

POSITIVE LOGITS

nesday

0.85

tch

0.77

JB

0.75

nec

0.73

eny

0.71

gery

0.70

robe

0.68

wordpress

0.66

stone

0.66

word

0.64

Activations Density 0.070%

proper nouns related to different named entities such as organizations, locations, and individuals

the special character end-of-text and instances of a specific entity or name

No Comments

No Known Activations