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

angel

-0.76

 Ambro

-0.74

>>\

-0.73

 elev

-0.72

 Vaugh

-0.71

ngth

-0.69

ð

-0.69

esson

-0.66

href

-0.66

ills

-0.66

POSITIVE LOGITS

 runaway

0.70

 anarchist

0.69

 spotted

0.68

ooters

0.64

 predicting

0.64

 autonomy

0.61

 flee

0.61

 pals

0.61

shy

0.60

 anarchists

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.