INDEX

Explanations

phrases and terms related to torture and interrogation practices

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

0:0.24

1:0.02

2:0.19

3:0.07

4:0.03

5:0.07

6:0.06

7:0.05

8:0.08

9:0.04

10:0.05

11:0.04

Negative Logits

 Valiant

-3.10

Hunt

-2.94

oire

-2.62

git

-2.60

Toy

-2.54

──

-2.52

 Vendor

-2.47

 Witcher

-2.47

 Targ

-2.46

 Hugo

-2.44

POSITIVE LOGITS

 dehuman

3.03

 immersion

2.97

 boarding

2.91

boarding

2.90

 indo

2.77

nap

2.66

 advoc

2.65

nas

2.65

 hypnot

2.64

 anesthesia

2.64

Activations Density 0.002%

phrases and terms related to torture and interrogation practices

No Comments

No Known Activations