INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.10

2:0.09

3:0.08

4:0.07

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Tradable

-1.79

 Laboratories

-1.60

 eminent

-1.54

 Alive

-1.52

 Wrong

-1.50

 Reserved

-1.49

 Contracts

-1.46

*/

-1.45

Him

-1.44

 Himself

-1.43

POSITIVE LOGITS

ucc

1.64

1.50

icro

1.49

 challeng

1.49

facing

1.47

GW

1.42

hitting

1.41

eli

1.40

sole

1.40

 canopy

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.