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

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Serv

-2.81

 briefings

-2.59

sels

-2.51

inis

-2.39

inse

-2.37

command

-2.30

reet

-2.25

Prin

-2.24

Laun

-2.24

ouk

-2.24

POSITIVE LOGITS

 Ragnar

2.85

onian

2.73

 Dynam

2.72

 MDMA

2.70

 anarchist

2.69

 Austrian

2.66

Benz

2.65

 exponent

2.64

 anarchism

2.64

 Riot

2.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.