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

agos

-0.71

gard

-0.69

illing

-0.69

gov

-0.67

 Trave

-0.63

yr

-0.62

aus

-0.62

rams

-0.61

 intern

-0.61

EMS

-0.60

POSITIVE LOGITS

yip

0.77

adobe

0.71

natureconservancy

0.70

ENTION

0.67

 Allaah

0.65

pour

0.65

animous

0.65

 appet

0.64

icult

0.63

ï¸

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.