INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.07

1:0.07

2:0.09

3:0.09

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.06

10:0.08

11:0.07

Negative Logits

terness

-2.69

VID

-2.55

TS

-2.53

*/(

-2.48

 Thro

-2.44

 Drivers

-2.44

phies

-2.41

NetMessage

-2.37

itone

-2.36

space

-2.35

POSITIVE LOGITS

 casinos

2.75

Kok

2.58

 Olymp

2.54

 creatine

2.52

Cro

2.48

 Croatia

2.47

Dj

2.47

ika

2.42

Kar

2.39

ça

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.