INDEX

Explanations

references to membership and statistics within organizations

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

0:0.04

1:0.04

2:0.04

3:0.05

4:0.06

5:0.03

6:0.09

7:0.36

8:0.03

9:0.05

10:0.04

11:0.11

Negative Logits

 Lans

-2.73

 segreg

-2.63

 Larson

-2.61

 Soldiers

-2.55

 sshd

-2.52

NetMessage

-2.45

 Kirk

-2.44

ak

-2.41

 Archdemon

-2.38

Rak

-2.38

POSITIVE LOGITS

wana

3.20

 Uruguay

3.05

 Fiji

3.04

NZ

2.97

amera

2.65

olphins

2.55

 Australian

2.54

��

2.54

izu

2.48

 Zeal

2.47

Activations Density 0.012%

references to membership and statistics within organizations

No Comments

No Known Activations