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

2:0.09

3:0.07

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Faction

-2.99

 elector

-2.69

 Syndicate

-2.65

 adapter

-2.65

slot

-2.60

 Dealer

-2.58

 audi

-2.57

 elig

-2.57

ghai

-2.55

 converter

-2.53

POSITIVE LOGITS

 Schwar

2.57

 Ches

2.49

 Pepper

2.45

onomous

2.37

 Scot

2.33

م

2.30

Wil

2.30

 Woody

2.28

 yawn

2.27

 Schwe

2.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.