INDEX

Explanations

terms related to gun rights and ownership

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.01

2:0.44

3:0.08

4:0.02

5:0.09

6:0.04

7:0.04

8:0.07

9:0.02

10:0.02

11:0.02

Negative Logits

 Europa

-3.02

 Ethiop

-2.85

 Ethiopia

-2.75

 Fiji

-2.67

 Atlantis

-2.56

iggurat

-2.51

 Juno

-2.48

 stagnation

-2.45

 labou

-2.45

Io

-2.43

POSITIVE LOGITS

 firearm

6.58

 firearms

6.56

 handguns

6.43

 Firearms

6.27

 handgun

6.26

gun

6.20

 guns

6.16

Gun

6.07

 Guns

5.63

NRA

5.49

Activations Density 0.466%

terms related to gun rights and ownership

No Comments

No Known Activations