INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ources

-0.67

cius

-0.66

herty

-0.65

needs

-0.63

uez

-0.62

 necessity

-0.60

Tot

-0.59

uckland

-0.59

speak

-0.58

ãĤ´ãĥ³

-0.58

POSITIVE LOGITS

isp

0.73

ijing

0.66

å§«

0.60

ishop

0.59

itz

0.59

Â®

0.59

igun

0.58

idate

0.58

ozy

0.58

ppy

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.