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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

deen

-0.74

ignty

-0.68

tes

-0.68

aws

-0.67

nar

-0.66

 slack

-0.65

erk

-0.65

ainer

-0.65

ankind

-0.65

urat

-0.63

POSITIVE LOGITS

soDeliveryDate

0.97

Winged

0.79

©¶æ

0.72

Doe

0.71

ILLE

0.70

ãĤ©

0.70

osate

0.68

URA

0.68

Fram

0.67

 Corinth

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.