INDEX

Explanations

content related to legal issues and violations of rights

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_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

0:0.28

1:0.04

2:0.06

3:0.05

4:0.06

5:0.04

6:0.09

7:0.09

8:0.01

9:0.06

10:0.08

11:0.07

Negative Logits

WWF

-4.18

Nar

-3.74

 Sharks

-3.60

 Scorp

-3.58

 Lash

-3.56

 resil

-3.47

 Hydro

-3.44

 Scorpion

-3.28

amphetamine

-3.27

Nar

-3.24

POSITIVE LOGITS

 baker

8.57

 bakery

7.93

 bake

7.00

 cakes

6.47

 baking

6.07

 Bake

5.76

 pastry

5.68

 baked

5.54

 cake

5.50

 bread

5.50

Activations Density 0.012%

content related to legal issues and violations of rights

No Comments

No Known Activations