INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

soDeliveryDate

-0.87

 Seym

-0.71

lins

-0.69

é¾įåĸļå£«

-0.67

 Compos

-0.66

 reinforcement

-0.65

Queen

-0.65

oru

-0.64

 Frames

-0.64

issance

-0.64

POSITIVE LOGITS

 sshd

0.86

pid

0.77

happy

0.62

ascript

0.62

perature

0.61

CVE

0.60

bably

0.60

akedown

0.59

 mushroom

0.59

bered

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.