INDEX

Explanations

instances of violence and its impact on society, particularly focusing on domestic violence and its representation through language

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

0:0.06

1:0.03

2:0.18

3:0.05

4:0.05

5:0.05

6:0.22

7:0.04

8:0.04

9:0.18

10:0.03

11:0.03

Negative Logits

 Frog

-3.74

FD

-3.69

 Dock

-3.68

FD

-3.56

 Keller

-3.56

GE

-3.42

 Hobby

-3.41

 Town

-3.41

 Ferry

-3.34

Dew

-3.30

POSITIVE LOGITS

violence

8.08

 violence

7.98

 Violence

7.93

 Violent

6.74

violent

6.74

Viol

6.69

 violent

6.59

 nonviolent

5.61

 brutality

4.58

 bloodshed

4.56

Activations Density 0.013%

instances of violence and its impact on society, particularly focusing on domestic violence and its representation through language

No Comments

No Known Activations