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

 congr

-0.69

 molecules

-0.66

ATURE

-0.65

ACP

-0.63

pg

-0.60

 Pharaoh

-0.60

ODUCT

-0.60

imus

-0.60

versely

-0.60

(<

-0.59

POSITIVE LOGITS

fal

0.69

Downloadha

0.62

fall

0.61

fter

0.60

ween

0.59

 isEnabled

0.58

oker

0.58

cession

0.58

 surrender

0.57

Fall

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.