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

buster

-0.73

TOP

-0.73

rants

-0.73

KA

-0.73

CONCLUS

-0.69

MN

-0.67

kW

-0.67

-0.66

lasses

-0.65

 STATES

-0.64

POSITIVE LOGITS

 moder

0.89

 abstinence

0.76

ettings

0.74

 Moder

0.72

 impression

0.72

 chatting

0.70

 texting

0.69

 Strait

0.67

 adolesc

0.66

 interf

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.