INDEX

Explanations

words related to enigmas or puzzles

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ques" and its variations, indicating a focus on questions or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

WC

-0.68

 damp

-0.65

sea

-0.64

Assembly

-0.63

 random

-0.63

 mids

-0.61

 artificial

-0.61

 separation

-0.60

Sharp

-0.60

 seas

-0.60

POSITIVE LOGITS

ues

1.43

ilver

1.18

creen

1.00

hift

0.96

uer

0.95

chool

0.93

ued

0.93

ugu

0.93

ue

0.91

terday

0.91

Activations Density 0.006%

words related to enigmas or puzzles

instances of the word "ques" and its variations, indicating a focus on questions or inquiries

No Comments

No Known Activations