INDEX

Explanations

terms related to tolerance policies, especially in the context of governance and behavior regulation

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.01

2:0.10

3:0.07

4:0.10

5:0.03

6:0.05

7:0.36

8:0.03

9:0.04

10:0.09

11:0.05

Negative Logits

estamp

-1.92

window

-1.70

 prototypes

-1.54

alter

-1.53

hook

-1.51

Ago

-1.51

�

-1.49

ements

-1.48

prints

-1.47

セ

-1.46

POSITIVE LOGITS

 cruelty

1.79

 Violence

1.72

 harassment

1.71

 abuse

1.69

 homophobia

1.66

 manslaughter

1.66

 dealing

1.65

 criminally

1.64

 racism

1.63

 discrimination

1.63

Activations Density 0.000%

terms related to tolerance policies, especially in the context of governance and behavior regulation

No Comments

No Known Activations