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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffff

-0.92

onne

-0.85

 occas

-0.82

uyomi

-0.78

ħĭ

-0.76

hops

-0.75

 accordingly

-0.73

utical

-0.73

psy

-0.71

cffffcc

-0.70

POSITIVE LOGITS

less

0.68

NG

0.66

II

0.65

 plural

0.63

UAL

0.63

Nad

0.61

 Model

0.60

 Celebrity

0.60

 offspring

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.