INDEX

Explanations

the word "Cr" followed by a single character or a series of characters

oai_token-act-pair · gpt-3.5-turbo

references to a specific character or person named "Crick."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

å§«

-0.92

eers

-0.82

DragonMagazine

-0.80

 Ukrainian

-0.77

IELD

-0.73

HCR

-0.73

 Werewolf

-0.69

 Remastered

-0.69

 GOODMAN

-0.68

 Wildcats

-0.68

POSITIVE LOGITS

adle

1.05

umb

0.93

ursor

0.89

utch

0.88

uder

0.87

umbs

0.87

acker

0.86

udge

0.85

anks

0.85

acies

0.84

Activations Density 0.006%

the word "Cr" followed by a single character or a series of characters

references to a specific character or person named "Crick."

No Comments

No Known Activations