INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Rich

-0.70

 saves

-0.67

 spreads

-0.67

minster

-0.65

 hurts

-0.65

 driveway

-0.64

aires

-0.59

iaries

-0.59

case

-0.58

Osh

-0.58

POSITIVE LOGITS

ombat

0.85

 Gleaming

0.79

merce

0.79

Ń·

0.79

sbm

0.78

EStream

0.76

ichen

0.72

ãĥīãĥ©

0.72

interstitial

0.72

Interstitial

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.