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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

boards

-0.81

 actionGroup

-0.79

 Â®

-0.77

heid

-0.73

hin

-0.69

enf

-0.69

cano

-0.67

hig

-0.66

chin

-0.66

bands

-0.64

POSITIVE LOGITS

tyr

0.72

iliary

0.66

 vulner

0.64

ople

0.63

ĨĴ

0.63

 proport

0.61

 Irving

0.60

 Watergate

0.60

Pod

0.59

Ļ½

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.