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

uras

-0.86

 fortun

-0.72

 neighb

-0.71

 incent

-0.70

 conflic

-0.69

èĢħ

-0.67

ascus

-0.67

 proport

-0.66

 outwe

-0.65

 princ

-0.65

POSITIVE LOGITS

mph

0.78

0.69

rations

0.69

sf

0.68

erness

0.67

graduate

0.66

Steven

0.65

VC

0.64

rl

0.64

comments

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.