INDEX

Explanations

specific references to measurements and financial implications

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

0:0.03

1:0.01

2:0.11

3:0.16

4:0.30

5:0.03

6:0.04

7:0.10

8:0.04

9:0.03

10:0.04

11:0.04

Negative Logits

 contrasted

-1.65

endant

-1.49

の魔

-1.46

 reminded

-1.43

 unconsciously

-1.42

 resembled

-1.40

 Slowly

-1.39

 differs

-1.38

 generously

-1.38

 Kend

-1.38

POSITIVE LOGITS

 anymore

1.80

usual

1.69

 Hague

1.69

 cutoff

1.65

 limitations

1.65

 tipping

1.56

 specifics

1.55

 requirements

1.55

 caveats

1.53

 equivalents

1.49

Activations Density 0.004%

specific references to measurements and financial implications

No Comments

No Known Activations