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

0:0.09

1:0.08

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.09

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

�

-2.78

afort

-2.78

Putin

-2.74

achine

-2.61

ASC

-2.54

Esk

-2.53

Chat

-2.53

 Constantin

-2.49

 privatization

-2.47

 exchanged

-2.42

POSITIVE LOGITS

SourceFile

2.79

 veto

2.74

 Governors

2.62

iversal

2.60

 Kirst

2.49

riet

2.47

 Heller

2.47

Hoy

2.44

ilities

2.40

 McDonnell

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.