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

Faw

-0.68

 bridge

-0.68

ulia

-0.67

 Vide

-0.65

 quotes

-0.61

vati

-0.61

 quotation

-0.60

 webcam

-0.59

aunch

-0.58

Cap

-0.58

POSITIVE LOGITS

asio

0.73

 Beir

0.71

asons

0.67

STDOUT

0.67

IOR

0.67

intendent

0.67

olt

0.66

Ì¶

0.66

Tile

0.66

agles

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.