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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ASE

-0.79

ances

-0.71

------------------------

-0.71

ilies

-0.68

OVA

-0.68

 âĢº

-0.64

ocal

-0.64

sey

-0.63

REF

-0.62

rawdownloadcloneembedreportprint

-0.61

POSITIVE LOGITS

ĸļ

0.76

senal

0.73

mercial

0.69

itionally

0.64

 Compass

0.63

ordering

0.62

nesday

0.62

userc

0.61

 rotated

0.61

terday

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.