INDEX

Explanations

the word "it"

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

1:0.08

2:0.07

3:0.08

4:0.07

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 continental

-2.66

Brow

-2.61

 cascade

-2.48

-2.37

 marine

-2.36

 neocons

-2.35

 unequiv

-2.35

 fasc

-2.35

 Article

-2.29

 geop

-2.26

POSITIVE LOGITS

Interstitial

3.53

////////////////////////////////

3.22

////////////////

2.93

////////

2.68

 Uriel

2.66

 Abbey

2.65

 Shinra

2.65

emp

2.62

raid

2.59

ptions

2.57

Activations Density 0.000%

the word "it"

No Comments

No Known Activations