INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

iations

-0.77

itudinal

-0.75

rams

-0.69

demand

-0.67

icals

-0.65

DPR

-0.65

ules

-0.61

 Dorothy

-0.60

 Disciple

-0.60

iculture

-0.60

POSITIVE LOGITS

nis

0.69

cas

0.68

wat

0.65

sung

0.63

burg

0.63

abet

0.63

boro

0.62

 divorce

0.61

finished

0.60

ptin

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.