INDEX

Explanations

punctuation used to delimit clauses or phrases

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.27

1:0.05

2:0.05

3:0.07

4:0.03

5:0.06

6:0.03

7:0.01

8:0.19

9:0.09

10:0.05

11:0.06

Negative Logits

 reconc

-1.52

 pent

-1.52

 horizont

-1.52

pees

-1.49

 notor

-1.38

 myst

-1.38

byter

-1.37

 sucker

-1.33

 Fein

-1.32

 Melvin

-1.32

POSITIVE LOGITS

etc

2.03

1.89

·

1.85

•

1.78

>)

1.70

 Installation

1.70

};

1.69

↵

1.65

Installation

1.64

 Horizon

1.59

Activations Density 0.001%

punctuation used to delimit clauses or phrases

No Comments

No Known Activations