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

riot

-0.78

¬¼

-0.76

 Confeder

-0.72

riots

-0.65

Uri

-0.65

 Ferdinand

-0.64

omes

-0.62

sections

-0.59

elaide

-0.58

 Scal

-0.57

POSITIVE LOGITS

swick

0.78

ragon

0.76

nos

0.72

 Caucasus

0.71

rill

0.71

xtap

0.71

pas

0.71

theless

0.70

pring

0.69

 yourselves

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.