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

risome

-0.76

asar

-0.74

ratulations

-0.73

ldon

-0.73

azar

-0.71

 Keller

-0.70

quo

-0.69

uled

-0.68

ãĥŀ

-0.68

uliffe

-0.68

POSITIVE LOGITS

amic

0.66

 weighs

0.64

feet

0.64

 Rebels

0.63

 Stra

0.62

 Tart

0.62

lege

0.62

mosp

0.62

borne

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.