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

 sacrific

-0.69

ulkan

-0.67

iameter

-0.67

berra

-0.67

 capsule

-0.64

avascript

-0.64

gren

-0.64

aug

-0.63

 lapt

-0.63

 moderator

-0.63

POSITIVE LOGITS

anty

0.68

BuyableInstoreAndOnline

0.67

 Walls

0.63

 Willie

0.61

Done

0.60

 Sahara

0.60

 Seasons

0.59

ordan

0.58

 Jungle

0.58

 Cant

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.