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

ardy

-0.77

Ļ½

-0.75

 Lumpur

-0.73

ellen

-0.70

iaz

-0.68

sembly

-0.68

 redes

-0.67

½

-0.66

etting

-0.66

terness

-0.65

POSITIVE LOGITS

move

0.70

|--

0.69

 Gutenberg

0.64

"/>

0.64

crime

0.64

 CrossRef

0.62

pit

0.62

acity

0.60

POV

0.59

selves

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.