INDEX

Explanations

instances of parentheses or similar punctuation

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

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

 streng

-2.71

 bowl

-2.57

cler

-2.46

uler

-2.46

CLOSE

-2.45

inous

-2.43

 aback

-2.40

 caval

-2.37

attacks

-2.34

 toget

-2.32

POSITIVE LOGITS

 Corsair

2.94

Ez

2.93

RP

2.90

VG

2.70

LTD

2.58

CCP

2.56

 ORIG

2.56

Kad

2.52

 Riot

2.48

 Rabb

2.47

Activations Density 0.000%

instances of parentheses or similar punctuation

No Comments

No Known Activations