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

 behold

-0.69

å·

-0.67

vous

-0.67

pheus

-0.66

Assembly

-0.66

ERC

-0.66

VL

-0.65

ĪĴ

-0.65

 assembly

-0.64

assemb

-0.63

POSITIVE LOGITS

 Colonial

0.76

hog

0.71

 downgrade

0.69

 Rebels

0.68

allo

0.67

 Notting

0.66

icester

0.66

tered

0.64

 Americ

0.63

 Mansion

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.