INDEX

Explanations

expressions related to decision-making and consequences

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

6:0.26

7:0.04

8:0.08

9:0.23

10:0.02

11:0.04

Negative Logits

 Harris

-4.05

Harris

-4.03

Dow

-3.65

atten

-3.65

 Briggs

-3.65

 Faul

-3.59

 Burton

-3.59

 Hots

-3.42

 Archdemon

-3.37

 Dele

-3.34

POSITIVE LOGITS

Rom

9.55

Rom

9.37

 Romero

8.70

ROM

7.30

ROM

6.48

rom

5.95

rom

5.41

Roman

5.38

 Roma

5.21

 Romans

5.06

Activations Density 0.001%

expressions related to decision-making and consequences

No Comments

No Known Activations