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

0:0.09

1:0.07

2:0.07

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.10

11:0.09

Negative Logits

 Staples

-2.48

 StarCraft

-2.37

 Hearthstone

-2.32

 Prospect

-2.22

 readers

-2.21

 differently

-2.20

 accordingly

-2.20

 deviation

-2.20

 Alter

-2.19

FX

-2.17

POSITIVE LOGITS

ierrez

2.83

gian

2.72

pees

2.59

ernand

2.57

Password

2.54

chal

2.46

uga

2.45

Pg

2.44

redibly

2.42

enne

2.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.