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

0:0.10

1:0.08

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.06

10:0.08

11:0.09

Negative Logits

umenthal

-2.74

croft

-2.52

erville

-2.51

romeda

-2.48

rique

-2.48

rich

-2.43

POL

-2.42

rawn

-2.42

hedral

-2.39

 Democr

-2.35

POSITIVE LOGITS

[/

2.83

 Females

2.62

 Alexa

2.54

SPD

2.53

 fetish

2.53

 Canary

2.52

 Clicker

2.44

 Pets

2.42

 Siren

2.40

 retard

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.