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

ĸļ

-0.76

lain

-0.66

olulu

-0.66

Override

-0.65

 holog

-0.64

onding

-0.62

 lact

-0.62

ultz

-0.61

 depos

-0.60

 Kent

-0.60

POSITIVE LOGITS

SF

0.67

sth

0.67

Wra

0.67

GL

0.65

 Fior

0.64

.}

0.62

 Browne

0.62

 Scheme

0.62

Gh

0.62

ictions

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.