INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

minist

-1.62

tein

-1.55

 output

-1.34

Sly

-1.34

 outper

-1.34

EPS

-1.29

 manuals

-1.27

MAG

-1.24

 Annotations

-1.24

 Grizz

-1.23

POSITIVE LOGITS

thia

1.76

anus

1.74

reditary

1.63

isha

1.54

erity

1.54

itia

1.52

ulhu

1.44

atever

1.44

etrical

1.43

rez

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.