INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

iors

-0.67

ruption

-0.65

mber

-0.63

heid

-0.62

Aid

-0.61

 rental

-0.61

NL

-0.61

 rentals

-0.59

 Rubin

-0.58

 pitchers

-0.58

POSITIVE LOGITS

maxwell

0.89

Princ

0.79

ãĤ´ãĥ³

0.74

hovah

0.72

 Written

0.71

agher

0.70

ists

0.70

Fuck

0.67

pract

0.67

ographically

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.