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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 antioxid

-0.70

 posit

-0.65

 ultras

-0.65

 inputs

-0.64

eas

-0.63

Ly

-0.63

:\

-0.62

 pregn

-0.61

Pic

-0.61

uno

-0.61

POSITIVE LOGITS

edia

1.01

urities

0.82

ashington

0.76

 Minotaur

0.74

rencies

0.71

eanor

0.68

apego

0.67

 Daylight

0.67

verning

0.67

leck

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.