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

1:0.07

2:0.08

3:0.10

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Entered

-3.35

 Mason

-3.32

 Setup

-3.13

SPONSORED

-3.12

 Kali

-3.11

 Miracle

-3.09

 Defeat

-3.09

 Greatest

-3.05

 Vital

-3.02

 Codec

-3.01

POSITIVE LOGITS

oppers

3.19

\":

2.72

packages

2.68

 plush

2.65

oys

2.62

othe

2.59

 humane

2.58

agos

2.58

 empath

2.57

agraph

2.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.