INDEX

Explanations

occurrences of the word "of."

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

endif

-1.83

END

-1.68

arn

-1.62

iffe

-1.57

end

-1.53

ondon

-1.52

igmat

-1.51

kill

-1.51

more

-1.50

ielding

-1.49

POSITIVE LOGITS

1.94

othermal

1.77

acly

1.62

 Thro

1.61

gdala

1.60

 Beet

1.57

rats

1.56

 concede

1.54

�

1.54

obbies

1.53

Activations Density 0.000%

occurrences of the word "of."

No Comments

No Known Activations