INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

uca

-0.69

TN

-0.64

quished

-0.60

channelAvailability

-0.59

iannopoulos

-0.59

 Regardless

-0.57

argon

-0.57

âĢ¦]

-0.57

otaur

-0.57

UTC

-0.56

POSITIVE LOGITS

1.39

âĢĳ

1.19

-$

0.92

-,

0.88

-'

0.83

-.

0.82

âĢĲ

0.81

"-

0.73

-[

0.72

%-

0.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.