INDEX

Explanations

instances of the word "in" indicating locations or contexts within the text

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

0:0.04

1:0.04

2:0.04

3:0.20

4:0.04

5:0.05

6:0.03

7:0.07

8:0.07

9:0.03

10:0.31

11:0.03

Negative Logits

 guiIcon

-2.07

 relative

-2.00

 irrespective

-1.98

 conditional

-1.96

 reproduce

-1.93

motion

-1.91

 cannot

-1.87

 substitution

-1.86

enf

-1.85

 combinations

-1.85

POSITIVE LOGITS

 circa

2.51

December

2.43

uesday

2.35

ixties

2.33

January

2.30

 shelves

2.23

 headquarters

2.20

February

2.19

hattan

2.19

2.17

Activations Density 0.009%

instances of the word "in" indicating locations or contexts within the text

No Comments

No Known Activations