INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.07

Negative Logits

 Seym

-3.30

pmwiki

-3.03

yne

-3.02

 bakery

-2.83

 Bake

-2.79

lishes

-2.77

 Pitch

-2.76

 mascara

-2.75

Adv

-2.64

 bake

-2.58

POSITIVE LOGITS

>>>>>>>>

3.06

�

2.83

>>>

2.65

enty

2.61

 ****

2.59

cong

2.58

uine

2.57

gg

2.55

hu

2.53

yip

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.