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

 Cutter

-0.86

 Cascade

-0.80

 Chaser

-0.79

 Volcano

-0.74

 volcan

-0.72

 cones

-0.69

 Crus

-0.68

 Cannon

-0.68

 petitions

-0.67

 Blast

-0.67

POSITIVE LOGITS

nen

0.84

London

0.79

ëĭ

0.75

NF

0.74

oros

0.74

mys

0.73

LA

0.73

oS

0.71

los

0.71

ny

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.