INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hound

-0.73

 balloons

-0.71

oard

-0.69

 Tunnel

-0.68

 Flask

-0.65

 Grande

-0.64

 Chambers

-0.63

ieg

-0.63

 Tayyip

-0.63

 redes

-0.63

POSITIVE LOGITS

awa

0.72

IOR

0.66

MFT

0.64

MENTS

0.64

bilt

0.64

Â«

0.63

omach

0.61

ior

0.61

iors

0.61

Effective

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.