INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Woodward

-0.65

éĹĺ

-0.64

natureconservancy

-0.61

ãĤ¤ãĥĪ

-0.61

odcast

-0.60

VEN

-0.60

 redundancy

-0.60

 Rodgers

-0.59

Offline

-0.59

Reviewer

-0.58

POSITIVE LOGITS

mouth

0.77

rolled

0.68

ridge

0.68

gest

0.67

ishers

0.65

ividual

0.65

cised

0.65

lund

0.64

ropolitan

0.63

icted

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.