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

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

"},{"

-3.34

"}

-2.70

 seism

-2.68

 proble

-2.64

"}],"

-2.55

 Geological

-2.47

effic

-2.46

 Hyder

-2.43

 footh

-2.42

venture

-2.42

POSITIVE LOGITS

 Duchess

3.57

 Nero

3.45

aucus

3.00

yip

2.85

 Tort

2.78

CTR

2.77

idy

2.66

Vul

2.64

 Lucius

2.63

fusc

2.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.