INDEX

Explanations

the presence of specific names or labels

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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

\":

-3.09

 Edmonton

-3.00

ipeg

-2.97

isSpecialOrderable

-2.91

thouse

-2.90

auga

-2.81

acid

-2.80

itent

-2.78

rush

-2.77

ument

-2.75

POSITIVE LOGITS

 Seah

2.94

 kosher

2.52

 veto

2.46

hei

2.43

 Bere

2.33

 homeland

2.33

 Lenovo

2.30

PL

2.28

 invitations

2.28

 McDonnell

2.26

Activations Density 0.000%

the presence of specific names or labels

No Comments

No Known Activations