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

verbs

-0.81

luster

-0.77

emale

-0.73

zos

-0.71

_-

-0.71

Rom

-0.70

 Recipes

-0.69

++++++++++++++++

-0.69

Legendary

-0.68

Stretch

-0.68

POSITIVE LOGITS

 repl

0.63

ococ

0.63

CPS

0.63

ourced

0.62

ifiers

0.62

 differe

0.61

romy

0.60

itu

0.60

 Patron

0.60

ership

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.