INDEX

Explanations

references to organizations or groups associated with the United States

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.02

2:0.14

3:0.03

4:0.05

5:0.03

6:0.19

7:0.24

8:0.03

9:0.02

10:0.14

11:0.04

Negative Logits

 regress

-1.89

 valve

-1.71

iquid

-1.68

 valves

-1.63

onz

-1.62

htaking

-1.61

mone

-1.56

 benz

-1.55

ebin

-1.51

ttp

-1.50

POSITIVE LOGITS

 Forestry

1.67

 Seventh

1.64

ogle

1.62

 Chaser

1.57

 Scouts

1.56

 Parade

1.56

aughtered

1.53

 Profession

1.51

NEC

1.51

 Oath

1.51

Activations Density 0.001%

references to organizations or groups associated with the United States

No Comments

No Known Activations