INDEX

Explanations

references to films, games, and online content

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.02

1:0.03

2:0.08

3:0.04

4:0.03

5:0.08

6:0.09

7:0.36

8:0.05

9:0.03

10:0.09

11:0.06

Negative Logits

alion

-1.49

iHUD

-1.25

nel

-1.21

osen

-1.20

ORD

-1.19

orem

-1.16

enance

-1.13

>:

-1.11

POL

-1.10

ulus

-1.08

POSITIVE LOGITS

 genres

1.54

 tabl

1.49

 genre

1.44

 magazines

1.44

 franchises

1.39

 autobi

1.38

rities

1.35

 notebooks

1.35

 starring

1.34

encers

1.33

Activations Density 0.209%

references to films, games, and online content

No Comments

No Known Activations