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

 reflections

-0.68

 Seym

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.66

wing

-0.62

 bubble

-0.61

 compose

-0.61

 Arkham

-0.61

 glasses

-0.60

 pilots

-0.60

 cockpit

-0.59

POSITIVE LOGITS

Published

0.84

bucks

0.69

ebook

0.67

Der

0.66

Source

0.66

 sidelines

0.65

article

0.65

Companies

0.65

wk

0.65

iera

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.