INDEX

Explanations

proper nouns, particularly names and titles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.15

1:0.17

2:0.06

3:0.07

4:0.02

5:0.02

6:0.09

7:0.10

8:0.03

9:0.03

10:0.17

11:0.03

Negative Logits

 Lear

-3.73

 Hearth

-3.50

 Granger

-3.03

 Bron

-3.02

 intrins

-2.76

 Latinos

-2.71

 loops

-2.65

 Malone

-2.62

LAT

-2.62

 Bees

-2.61

POSITIVE LOGITS

Fuk

8.03

uk

4.77

Muk

4.38

Ruk

4.13

Yuk

3.85

Luk

3.79

Suk

3.41

uku

3.40

Kum

3.30

 Sapp

3.28

Activations Density 0.001%

proper nouns, particularly names and titles

No Comments

No Known Activations