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

indal

-0.83

LO

-0.72

alone

-0.70

untu

-0.70

abal

-0.69

rontal

-0.69

oya

-0.67

ÏĢ

-0.65

osure

-0.64

Ħ¢

-0.64

POSITIVE LOGITS

hurst

0.68

fed

0.66

 Bayer

0.65

Plex

0.65

 Summers

0.64

etime

0.64

episode

0.63

 undisclosed

0.63

axis

0.63

Fed

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.