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

1:0.05

2:0.07

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

bud

-2.70

 Flor

-2.65

 Fell

-2.62

rh

-2.60

 Feel

-2.52

Dru

-2.52

hal

-2.49

Rey

-2.48

 Iris

-2.46

 Quan

-2.46

POSITIVE LOGITS

kefeller

3.26

 casinos

3.21

ufact

3.14

ataka

2.91

nikov

2.91

 piston

2.85

TNT

2.83

 Amtrak

2.82

ertodd

2.78

 casino

2.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.