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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouston

-0.75

 Pione

-0.61

 bicy

-0.61

java

-0.61

 Expand

-0.60

course

-0.60

 engineering

-0.60

 Elon

-0.59

audio

-0.58

 unanim

-0.58

POSITIVE LOGITS

raped

0.71

itz

0.69

 unden

0.66

ilan

0.65

SOURCE

0.64

Ñĭ

0.64

bledon

0.63

ords

0.63

rug

0.60

seys

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.