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

âķĲâķĲ

-0.75

UTERS

-0.71

éĹĺ

-0.69

ãĥ©ãĥ³

-0.67

thumbnails

-0.67

 Leban

-0.66

âĸĪâĸĪ

-0.66

anamo

-0.66

 Canaver

-0.66

 COUNTY

-0.65

POSITIVE LOGITS

idth

0.72

ominated

0.71

 unfocusedRange

0.66

rium

0.65

hin

0.64

sylv

0.63

 toughest

0.63

vana

0.63

rior

0.62

gal

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.