INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rait

-0.70

)</

-0.68

 Tradable

-0.66

uates

-0.65

scrib

-0.64

romeda

-0.64

izoph

-0.64

natureconservancy

-0.63

Wik

-0.63

thus

-0.62

POSITIVE LOGITS

 depreciation

0.71

 wolf

0.63

guyen

0.60

 Diet

0.60

 Temp

0.60

 Wolfe

0.59

pelling

0.58

 Engel

0.58

 migr

0.58

itri

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.