INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

insula

-0.74

jer

-0.71

sed

-0.70

Jer

-0.67

abol

-0.67

pn

-0.67

olor

-0.66

TOR

-0.65

ratulations

-0.64

arkin

-0.64

POSITIVE LOGITS

SX

0.68

 demos

0.68

orce

0.67

 demo

0.65

 agre

0.64

ufact

0.64

oti

0.63

fell

0.62

VG

0.62

Wim

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.