INDEX

Explanations

No Explanations Found

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

[|

-0.74

 Improvement

-0.71

 iterations

-0.64

å¼

-0.64

 Echoes

-0.63

mentioned

-0.62

ãĥīãĥ©

-0.62

 iteration

-0.62

 playthrough

-0.61

sts

-0.61

POSITIVE LOGITS

 Flavoring

0.80

ourgeois

0.73

atorial

0.72

iffe

0.72

ueller

0.72

ilet

0.71

anguage

0.69

ouver

0.68

azo

0.66

que

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.