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

é¾įåĸļå£«

-0.88

jamin

-0.82

Marx

-0.76

clips

-0.75

oyd

-0.75

ames

-0.73

fit

-0.71

ASED

-0.71

ihil

-0.71

dimension

-0.70

POSITIVE LOGITS

 Spotlight

0.73

CT

0.71

 Misty

0.70

 Mulcair

0.69

 firewall

0.69

 immunity

0.68

 Spectre

0.68

 Rubio

0.67

 Surge

0.67

 Hulu

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.