INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ULT

-0.96

Vector

-0.68

HOW

-0.68

KH

-0.68

Hack

-0.67

SF

-0.66

HOU

-0.66

ONES

-0.66

HQ

-0.66

HCR

-0.64

POSITIVE LOGITS

lde

0.77

ede

0.72

nda

0.66

grain

0.66

luent

0.66

udi

0.66

elin

0.65

 consum

0.65

hered

0.63

interstitial

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.