INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entric

-0.78

alach

-0.73

 actionGroup

-0.70

 guiActiveUnfocused

-0.69

 streng

-0.68

sburgh

-0.67

edo

-0.66

 ACTIONS

-0.65

appiness

-0.63

shape

-0.63

POSITIVE LOGITS

£ı

0.83

endez

0.78

Gaza

0.67

enium

0.66

raph

0.64

 Beir

0.63

JV

0.63

estone

0.63

 intraven

0.62

thur

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.