INDEX

Explanations

references to social media interactions and mentions of individuals

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.02

2:0.05

3:0.03

4:0.05

5:0.03

6:0.17

7:0.05

8:0.05

9:0.36

10:0.02

11:0.03

Negative Logits

osa

-3.84

esta

-3.53

 Kush

-3.45

roxy

-3.32

Sph

-3.29

Egypt

-3.26

 Prescott

-3.25

Els

-3.18

emis

-3.17

 Jupiter

-3.16

POSITIVE LOGITS

 Brian

8.35

Brian

8.24

 Brendan

5.09

 Bray

4.79

Brend

4.37

 Bobby

4.07

 Bryan

4.02

 Bour

3.84

Bri

3.82

 Conor

3.76

Activations Density 0.006%

references to social media interactions and mentions of individuals

No Comments

No Known Activations