INDEX

Explanations

instances of dialogue and impactful statements

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

0:0.13

1:0.02

2:0.06

3:0.04

4:0.04

5:0.03

6:0.15

7:0.05

8:0.10

9:0.27

10:0.02

11:0.03

Negative Logits

unia

-3.60

obyl

-3.50

 Belarus

-3.44

eka

-3.31

 Yanuk

-3.29

REM

-3.27

 Greenpeace

-3.20

democracy

-3.15

mt

-3.12

 synth

-3.10

POSITIVE LOGITS

 Fitzgerald

11.48

gerald

7.66

 Fitz

6.70

 Fitzpatrick

4.82

 Fowler

4.48

 Dickinson

4.24

 Gallagher

4.19

 Faul

4.06

 Cork

4.04

Gall

3.91

Activations Density 0.001%

instances of dialogue and impactful statements

No Comments

No Known Activations