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

1:0.08

2:0.07

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.07

Negative Logits

Ö

-3.18

inho

-3.11

 Bauer

-2.97

allas

-2.92

版

-2.91

Jose

-2.85

iverpool

-2.78

я

-2.78

ğ

-2.77

usk

-2.75

POSITIVE LOGITS

 Lyndon

2.79

 Twitch

2.67

 obnoxious

2.43

bill

2.41

 deleg

2.38

 entertain

2.38

VO

2.37

 consistently

2.36

 twitch

2.31

 Donation

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.