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

-0.69

NI

-0.68

geon

-0.67

recogn

-0.67

 Decay

-0.64

crow

-0.64

amen

-0.64

register

-0.64

Write

-0.62

amin

-0.62

POSITIVE LOGITS

[|

0.78

å£«

0.74

itol

0.63

Į

0.60

 aborted

0.60

¯

0.58

Lis

0.58

 credits

0.58

onymous

0.58

Pg

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.