INDEX

Explanations

phrases related to life and existence

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

0:0.02

1:0.02

2:0.09

3:0.05

4:0.23

5:0.02

6:0.13

7:0.24

8:0.03

9:0.03

10:0.05

11:0.04

Negative Logits

*/(

-1.68

Cola

-1.56

ortium

-1.51

 Citation

-1.50

stable

-1.50

 guiIcon

-1.50

bernatorial

-1.45

 Telescope

-1.39

Interested

-1.38

iculty

-1.38

POSITIVE LOGITS

 Venezuel

1.58

 eternity

1.51

 fantasies

1.49

 HELL

1.49

 adolesc

1.49

 Millennials

1.48

 embodied

1.45

Khe

1.42

 dads

1.41

 Colomb

1.40

Activations Density 0.000%

phrases related to life and existence

No Comments

No Known Activations