INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

obo

-0.81

peria

-0.74

opsis

-0.72

 flock

-0.71

orio

-0.71

ogo

-0.71

 snapped

-0.67

 sacked

-0.63

chini

-0.62

aptop

-0.62

POSITIVE LOGITS

////////

0.72

WE

0.70

èª

0.69

=-=-

0.66

 experien

0.65

SHA

0.64

ALSE

0.64

Chall

0.62

NEY

0.62

UGC

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.