INDEX

Explanations

references to research studies and analyses

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

0:0.02

1:0.02

2:0.02

3:0.04

4:0.16

5:0.32

6:0.03

7:0.03

8:0.01

9:0.26

10:0.01

11:0.03

Negative Logits

enty

-2.82

 unless

-2.80

 Leilan

-2.79

atra

-2.75

natureconservancy

-2.59

unless

-2.57

 dearly

-2.50

 Subtle

-2.48

 anyway

-2.45

 stay

-2.43

POSITIVE LOGITS

 reveals

5.24

 suggests

5.17

 confirms

5.08

 concluded

5.01

 showed

5.00

 indicates

4.93

 revealed

4.84

 predicts

4.63

 indicated

4.61

 concludes

4.55

Activations Density 0.309%

references to research studies and analyses

No Comments

No Known Activations