INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

oux

-0.76

HM

-0.68

gat

-0.67

sonian

-0.67

 Clarkson

-0.66

olt

-0.66

ulating

-0.66

 Wally

-0.65

ÃŃs

-0.65

 Omega

-0.65

POSITIVE LOGITS

tein

0.92

 assumption

0.82

 conflic

0.81

 latter

0.81

catentry

0.77

 possibility

0.76

 slightest

0.75

 upside

0.75

 feds

0.73

 Refuge

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.