INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Pg

-0.83

erella

-0.82

eenth

-0.81

AppData

-0.74

answered

-0.71

furt

-0.71

MORE

-0.69

iably

-0.69

apon

-0.68

 guiActiveUn

-0.68

POSITIVE LOGITS

 Brus

0.69

mu

0.67

 variation

0.64

STL

0.63

 variance

0.61

 vector

0.60

 pastoral

0.59

ops

0.59

 fragmentation

0.58

 vectors

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.