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

UTC

-0.81

egal

-0.79

Cart

-0.78

?ãĢį

-0.77

Bear

-0.70

?]

-0.70

Adds

-0.70

beard

-0.68

âĢ¦]

-0.68

wcs

-0.67

POSITIVE LOGITS

berus

0.68

 Wink

0.68

 behalf

0.66

oun

0.66

Mub

0.66

 Mehran

0.64

 Hyundai

0.62

manuel

0.61

ezvous

0.61

iltr

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.