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

1:0.09

2:0.09

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

 fasc

-2.67

 Paradox

-2.62

gal

-2.62

��

-2.51

gat

-2.43

Hav

-2.30

 Constantin

-2.29

GD

-2.29

 rainbow

-2.29

 Colomb

-2.28

POSITIVE LOGITS

emort

2.81

 tradem

2.79

 Somers

2.74

redients

2.65

ighth

2.63

overy

2.57

ients

2.55

ussion

2.50

oes

2.45

yden

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.