INDEX

Explanations

punctuated statements or expressions of emphasis

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

0:0.03

1:0.06

2:0.02

3:0.07

4:0.07

5:0.08

6:0.07

7:0.05

8:0.05

9:0.21

10:0.05

11:0.19

Negative Logits

..."

-2.91

 Appeal

-2.66

)|

-2.56

 conven

-2.51

?]

-2.51

.」

-2.46

 Advice

-2.43

 conduc

-2.39

 Appeals

-2.37

----

-2.37

POSITIVE LOGITS

lot

2.60

 Peyton

2.58

 William

2.50

strings

2.45

Whit

2.45

Von

2.40

 Floyd

2.39

 Scha

2.38

 Clintons

2.38

olph

2.38

Activations Density 0.003%

punctuated statements or expressions of emphasis

No Comments

No Known Activations