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

Head Attr Weights

0:0.07

1:0.08

2:0.07

3:0.09

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.06

11:0.08

Negative Logits

ⓘ

-2.74

Pwr

-2.70

的

-2.65

senal

-2.49

 Berkshire

-2.47

staking

-2.41

MpServer

-2.39

 Rothschild

-2.39

sembly

-2.38

 Argentine

-2.33

POSITIVE LOGITS

 Waters

2.49

 arenas

2.30

�

2.30

 themes

2.25

hani

2.25

hift

2.24

posts

2.21

 Lean

2.17

Ari

2.17

 contests

2.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.