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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 timeless

-2.82

 crooked

-2.65

 Twist

-2.55

 scrut

-2.54

 rests

-2.54

 Plot

-2.52

 weekday

-2.49

 Slide

-2.48

 Valerie

-2.48

fid

-2.47

POSITIVE LOGITS

odox

3.55

inventoryQuantity

3.43

 UCHIJ

3.27

Raid

3.21

agame

3.14

nih

3.02

amins

3.01

kus

2.98

AMD

2.97

ansky

2.96

Activations Density 0.000%

No Known Activations

This feature has no known activations.