INDEX

Explanations

rhetorical questions

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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.10

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

 pestic

-2.82

UID

-2.75

 prostitute

-2.70

 taxis

-2.68

ゴン

-2.67

nil

-2.66

agogue

-2.65

brates

-2.65

 Gujar

-2.55

Magikarp

-2.52

POSITIVE LOGITS

Lay

2.82

 tougher

2.54

 drilled

2.53

·

2.48

 Warren

2.39

Kry

2.38

 Lana

2.35

 Kane

2.34

nyder

2.32

 Witt

2.29

Activations Density 0.000%

rhetorical questions

No Comments

No Known Activations