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

Jed

-0.67

Jos

-0.67

Wim

-0.65

 Carney

-0.65

 Correspond

-0.65

 Panc

-0.63

 Laurent

-0.63

 Patt

-0.63

achable

-0.63

ta

-0.62

POSITIVE LOGITS

asta

0.73

ħĭ

0.71

gross

0.70

aby

0.70

sticks

0.69

stakes

0.68

 Tradable

0.67

species

0.66

Snake

0.65

ramid

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.