INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

wcsstore

-0.81

lihood

-0.75

tip

-0.75

hetically

-0.75

-0.72

yip

-0.70

hetical

-0.69

ierrez

-0.69

thumbnails

-0.67

UV

-0.67

POSITIVE LOGITS

 Inher

0.70

atton

0.64

anism

0.63

 civilisation

0.62

ihil

0.62

 Madness

0.60

ophys

0.59

iol

0.58

 scramble

0.57

 spoil

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.