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

0:0.07

1:0.07

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

arius

-2.97

ム

-2.92

achine

-2.89

ridor

-2.88

veyard

-2.87

ヴ

-2.86

ocy

-2.83

early

-2.75

numbered

-2.74

aiden

-2.74

POSITIVE LOGITS

 puppet

3.14

AMA

3.07

 pupp

2.78

 Million

2.76

 Knicks

2.75

 Dude

2.67

 newsp

2.58

TMZ

2.55

 Silk

2.54

 Manip

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.