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

inet

-0.74

ophe

-0.67

laughter

-0.64

plain

-0.63

 Swanson

-0.62

Ã³n

-0.60

 Presbyterian

-0.60

 pupil

-0.58

orian

-0.57

 Adds

-0.57

POSITIVE LOGITS

ternity

0.72

 Territories

0.69

 Worlds

0.68

FW

0.68

cum

0.66

otin

0.66

eco

0.66

aband

0.65

assi

0.65

azo

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.