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

1:0.08

2:0.07

3:0.08

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

games

-3.05

デ

-2.96

を

-2.92

Japanese

-2.87

Nintendo

-2.86

き

-2.84

scenes

-2.80

ゴン

-2.75

Japan

-2.75

モ

-2.74

POSITIVE LOGITS

Haf

3.08

 Ramsey

2.88

 barb

2.69

dow

2.69

Pry

2.56

 Juven

2.53

icka

2.49

zona

2.48

vir

2.46

wives

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.