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

lling

-0.69

 jour

-0.66

-0.65

icable

-0.62

obiles

-0.61

 neuroscience

-0.61

 recons

-0.60

 interviewing

-0.59

 sciences

-0.59

lled

-0.59

POSITIVE LOGITS

 Grip

0.73

Wem

0.73

iston

0.72

 Nanto

0.70

iolet

0.69

 Quality

0.68

 Seym

0.67

 Coastal

0.67

 Features

0.66

NER

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.