INDEX

Explanations

the word "only."

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.09

2:0.09

3:0.06

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 shuttle

-2.75

oyal

-2.68

occup

-2.62

 roam

-2.60

tank

-2.58

 recycle

-2.53

 locker

-2.53

 disposable

-2.51

 fleet

-2.51

 careg

-2.50

POSITIVE LOGITS

 Bach

3.10

 Herbert

2.78

Suc

2.74

Georgia

2.60

 Carolina

2.57

 Spur

2.54

Maria

2.53

Mand

2.53

 Durham

2.53

 Gamb

2.50

Activations Density 0.000%

the word "only."

No Comments

No Known Activations