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

 Modes

-0.75

mpeg

-0.70

ersive

-0.70

Adv

-0.68

 Hyder

-0.65

igator

-0.62

reports

-0.61

ACS

-0.61

uv

-0.61

 Incarn

-0.60

POSITIVE LOGITS

 borrowed

0.70

itual

0.66

atically

0.66

rained

0.66

erella

0.64

liest

0.64

å¤©

0.64

 Chaff

0.64

 Syri

0.63

 borrow

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.