INDEX

Explanations

references to incidents of violence and terrorism

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

0:0.10

1:0.02

2:0.03

3:0.05

4:0.06

5:0.26

6:0.03

7:0.07

8:0.03

9:0.24

10:0.02

11:0.04

Negative Logits

"!

-2.60

!".

-2.40

 anymore

-2.35

CTV

-2.30

 breeze

-2.20

 Chrys

-2.19

 doesnt

-2.10

phia

-2.10

!",

-2.08

ible

-2.06

POSITIVE LOGITS

ゼウス

2.50

 earlier

2.35

�

2.29

soType

2.29

�

2.25

arthed

2.24

ihadi

2.23

forcement

2.21

athing

2.20

 before

2.16

Activations Density 0.025%

references to incidents of violence and terrorism

No Comments

No Known Activations