INDEX

Explanations

mentions of police and public safety incidents

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

0:0.03

1:0.02

2:0.03

3:0.07

4:0.09

5:0.07

6:0.07

7:0.06

8:0.02

9:0.10

10:0.03

11:0.36

Negative Logits

 neoc

-2.34

 thinkers

-2.34

 curves

-2.33

 admire

-2.26

galitarian

-2.23

 experiments

-2.22

 pioneered

-2.19

 Millennials

-2.17

 philosoph

-2.16

 collaborations

-2.14

POSITIVE LOGITS

 spokesman

3.71

 spokesperson

3.51

 statement

3.42

 spokeswoman

3.36

 sheriff

2.99

 official

2.97

 dispatcher

2.85

 website

2.82

 Sheriff

2.77

 news

2.74

Activations Density 0.232%

mentions of police and public safety incidents

No Comments

No Known Activations