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

verages

-0.77

 Cosponsors

-0.68

 newsp

-0.68

 recip

-0.67

atural

-0.63

SPONSORED

-0.63

afety

-0.62

panic

-0.62

escape

-0.61

idae

-0.61

POSITIVE LOGITS

azeera

0.73

ibr

0.71

ancer

0.67

paper

0.66

 Theresa

0.64

LP

0.64

azo

0.62

lip

0.61

label

0.60

 Melania

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.