INDEX

Explanations

phrases related to desertion or abandonment

oai_token-act-pair · gpt-3.5-turbo

instances of abandonment and the concept of curry

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

yss

-0.81

ijk

-0.74

osate

-0.73

alions

-0.73

atoon

-0.71

 Ange

-0.68

uesday

-0.66

oppable

-0.66

astically

-0.65

es

-0.65

POSITIVE LOGITS

ãĥ¼ãĥĨ

0.95

quer

0.75

ney

0.73

neau

0.73

pil

0.70

æ©

0.70

ior

0.69

 glide

0.65

tesy

0.65

ãĤ¢ãĥ«

0.64

Activations Density 0.022%

phrases related to desertion or abandonment

instances of abandonment and the concept of curry

No Comments

No Known Activations