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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.09

10:0.07

11:0.07

Negative Logits

awaru

-2.91

 monkey

-2.88

 frog

-2.85

 shaman

-2.81

isher

-2.79

 monkeys

-2.79

ヤ

-2.72

FX

-2.58

-2.52

 Okawaru

-2.48

POSITIVE LOGITS

 Pasadena

2.96

 Worcester

2.90

 Areas

2.86

campus

2.81

Row

2.77

hattan

2.71

District

2.69

arnaev

2.65

Michigan

2.63

orable

2.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.