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

onna

-0.70

apixel

-0.70

thood

-0.69

)]

-0.69

oji

-0.69

CLOSE

-0.67

TPPStreamerBot

-0.67

rique

-0.67

aughs

-0.64

osponsors

-0.64

POSITIVE LOGITS

 annexed

0.74

auri

0.68

ICLE

0.64

lod

0.63

obin

0.62

unal

0.60

MIN

0.60

 WANT

0.60

inement

0.59

 Terminator

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.