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

mist

-0.77

wake

-0.71

keyes

-0.71

 Mans

-0.70

fulness

-0.69

emetery

-0.68

byss

-0.66

emis

-0.64

ongyang

-0.64

mental

-0.61

POSITIVE LOGITS

 Balkans

0.64

 cozy

0.61

 Prov

0.60

 CLIENT

0.60

 Pepper

0.58

nick

0.58

anka

0.58

arty

0.58

acements

0.57

 cough

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.