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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 interf

-0.73

 infiltr

-0.64

 homosexual

-0.63

 monitors

-0.62

UFO

-0.61

================

-0.61

Vector

-0.61

 navig

-0.60

DOS

-0.60

 improv

-0.59

POSITIVE LOGITS

rowth

0.78

 dstg

0.72

 snap

0.68

anners

0.65

arton

0.65

erva

0.64

 shards

0.64

most

0.64

eping

0.63

urers

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.