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

pedia

-0.87

blogs

-0.82

ebin

-0.81

poons

-0.76

AFTA

-0.73

owler

-0.72

©¶æ¥µ

-0.71

ĺħ

-0.70

 tempted

-0.68

sites

-0.67

POSITIVE LOGITS

 Illum

0.72

 DeVos

0.68

bie

0.66

chy

0.65

amara

0.63

 Ridley

0.62

resso

0.60

posal

0.59

mine

0.58

MON

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.