INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 confir

-0.80

swe

-0.72

drm

-0.70

grounds

-0.68

 Homo

-0.67

ogly

-0.65

 removal

-0.64

wagen

-0.63

HUD

-0.63

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.61

POSITIVE LOGITS

Catal

0.68

Liter

0.67

Series

0.66

Discuss

0.66

 Â®

0.66

Document

0.63

Moon

0.62

plings

0.60

pling

0.60

 Topic

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.