INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

vre

-2.83

orce

-2.78

ugu

-2.77

merce

-2.77

adobe

-2.75

clipse

-2.63

agos

-2.60

raft

-2.57

 reuse

-2.56

eret

-2.54

POSITIVE LOGITS

 Coliseum

3.00

 Station

2.90

 Sullivan

2.74

 Manit

2.70

 Cassidy

2.56

 deserving

2.56

 Knox

2.54

Tun

2.47

 Helsinki

2.47

 Stadium

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.