INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Kay

-0.78

olson

-0.76

 Haley

-0.72

Upload

-0.70

 Salman

-0.70

kin

-0.69

acho

-0.69

oj

-0.66

urat

-0.66

iona

-0.66

POSITIVE LOGITS

mates

0.62

 electrons

0.61

ymph

0.60

 Agricultural

0.60

 divided

0.60

cx

0.59

 Statistical

0.59

 particle

0.59

Pyr

0.59

GGGG

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.