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

BACK

-0.72

 Hatch

-0.71

 Vert

-0.67

ulse

-0.64

mc

-0.63

 McCorm

-0.62

 Kinnikuman

-0.62

IUM

-0.61

Mex

-0.61

kW

-0.61

POSITIVE LOGITS

pol

0.86

astically

0.79

arthed

0.75

ailable

0.75

tested

0.74

worldly

0.73

chal

0.73

ishly

0.71

entle

0.70

 arbitration

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.