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

Analy

-0.78

essler

-0.71

 Plot

-0.70

ambo

-0.69

analy

-0.69

 boycot

-0.67

plot

-0.66

 informants

-0.64

CLASSIFIED

-0.63

 affili

-0.63

POSITIVE LOGITS

Obj

0.71

AAA

0.68

heim

0.64

anos

0.62

livion

0.61

nell

0.60

apsed

0.59

ĸļ

0.59

TJ

0.59

 speeds

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.