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

Hex

-0.66

Prop

-0.65

itted

-0.65

ishly

-0.62

 hashing

-0.62

 Sons

-0.61

 Clause

-0.60

 Sabbath

-0.60

 hive

-0.60

geries

-0.60

POSITIVE LOGITS

VICE

0.71

vernment

0.69

 DRAG

0.68

CN

0.64

DN

0.64

 Lisbon

0.61

 associations

0.61

 Balkans

0.60

BILITIES

0.60

orie

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.