INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

irlf

-0.70

 pose

-0.68

NetMessage

-0.67

opoulos

-0.64

heastern

-0.63

ricks

-0.63

ryu

-0.62

 juven

-0.62

verages

-0.61

rient

-0.61

POSITIVE LOGITS

SpaceEngineers

0.81

Footnote

0.79

å§«

0.76

ãĤ¨ãĥ«

0.74

×ª

0.71

 fixme

0.69

seconds

0.68

ï¿½ï¿½ï¿½ï¿½

0.64

 Scouts

0.64

ï¿½ï¿½ï¿½

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.