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

obile

-0.72

 versa

-0.68

 grill

-0.64

 restaurant

-0.61

 Restaurant

-0.60

ALLY

-0.60

 Menu

-0.60

 preferences

-0.59

itialized

-0.58

oday

-0.58

POSITIVE LOGITS

 Typh

0.80

iard

0.79

fits

0.72

uminati

0.68

 Rowling

0.67

 Deity

0.66

Guard

0.65

stellar

0.65

bear

0.64

ternity

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.