INDEX

Explanations

punctuation, specifically commas

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

1:0.08

2:0.09

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.07

9:0.09

10:0.09

11:0.07

Negative Logits

 boots

-2.49

 combatants

-2.40

 footwear

-2.36

 apes

-2.33

ape

-2.32

 arte

-2.32

 parsed

-2.31

 vagina

-2.30

Foot

-2.29

 mould

-2.28

POSITIVE LOGITS

"@

2.71

ulton

2.66

��

2.53

ull

2.48

 Greenberg

2.47

 Jarrett

2.41

 Rosenberg

2.39

uls

2.38

ivating

2.35

liner

2.35

Activations Density 0.000%

punctuation, specifically commas

No Comments

No Known Activations