INDEX

Explanations

phrases related to expectations or predictions

oai_token-act-pair · gpt-3.5-turbo

references to specific excerpts or sections within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Sawyer

-0.71

 GOODMAN

-0.71

OOD

-0.66

LIN

-0.65

enegger

-0.64

NING

-0.63

 Rough

-0.61

WARE

-0.61

 scaff

-0.59

die

-0.59

POSITIVE LOGITS

haust

1.39

cerpt

1.27

terior

1.26

cessive

1.25

pert

1.24

ternally

1.23

ceptions

1.22

clamation

1.20

changes

1.18

pect

1.18

Activations Density 0.031%

phrases related to expectations or predictions

references to specific excerpts or sections within documents

No Comments

No Known Activations