INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Tao

-0.68

 suspended

-0.67

lua

-0.66

andal

-0.66

ardy

-0.64

assium

-0.64

icable

-0.64

ection

-0.64

ylum

-0.63

ulated

-0.62

POSITIVE LOGITS

å§«

0.79

LECT

0.69

ï¸ı

0.66

 comprehens

0.65

æ©

0.64

ellig

0.63

::::::::

0.63

 proble

0.63

å¤©

0.62

åħī

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.