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

0:0.09

1:0.08

2:0.08

3:0.07

4:0.07

5:0.06

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

gt

-2.83

Lap

-2.72

Lug

-2.70

wcsstore

-2.65

 Stud

-2.58

 Akron

-2.54

OU

-2.38

 Plat

-2.34

 Bowling

-2.32

DU

-2.32

POSITIVE LOGITS

 redund

2.81

hyde

2.71

pmwiki

2.54

 resil

2.47

agos

2.40

 dilig

2.40

roll

2.40

avin

2.35

ream

2.34

��

2.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.