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

 Voices

-0.70

 Pradesh

-0.66

 casting

-0.64

 tuning

-0.62

ONSORED

-0.61

 Represent

-0.61

ancers

-0.60

 midterm

-0.60

shire

-0.59

 genders

-0.58

POSITIVE LOGITS

pd

0.72

\/\/

0.71

bug

0.69

 ransom

0.67

á¸

0.67

none

0.66

miss

0.64

cule

0.63

 sack

0.63

thora

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.