INDEX

Explanations

content related to statements of potential issues and community responses

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

0:0.20

1:0.05

2:0.07

3:0.09

4:0.06

5:0.04

6:0.08

7:0.17

8:0.03

9:0.03

10:0.09

11:0.06

Negative Logits

 Castro

-3.45

 Sharma

-3.31

 Sagan

-3.17

 Rouhani

-3.13

 Azerbai

-3.00

 atomic

-2.98

 Shir

-2.95

 Kazakh

-2.95

 Rosenthal

-2.92

Sz

-2.85

POSITIVE LOGITS

EA

6.50

 Madden

4.63

EA

4.37

 Battlefield

4.22

hesda

3.97

Xbox

3.92

 Activision

3.81

 gamer

3.73

 gamers

3.60

 Xbox

3.51

Activations Density 0.003%

content related to statements of potential issues and community responses

No Comments

No Known Activations