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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pection

-0.77

ibrary

-0.76

yton

-0.73

phrine

-0.71

hops

-0.67

retty

-0.66

ounty

-0.66

igue

-0.64

wreck

-0.63

ifled

-0.63

POSITIVE LOGITS

 Â«

0.77

éĢ

0.69

kl

0.69

ãĤ¡

0.64

 referen

0.63

 Slip

0.62

âĦ¢:

0.62

<<

0.62

0.60

vi

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.