INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

lvl

-0.75

eer

-0.67

icon

-0.66

ãĥĩ

-0.64

Deal

-0.64

-0.61

 dream

-0.60

ãĥı

-0.59

Cly

-0.58

Cub

-0.58

POSITIVE LOGITS

\/\/

0.97

umatic

0.79

amation

0.71

Ã»

0.71

ousy

0.69

nery

0.66

inventory

0.66

bourg

0.64

emis

0.64

uria

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.