INDEX

Explanations

references to physical locations or structures

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.07

3:0.08

4:0.09

5:0.07

6:0.07

7:0.08

8:0.09

9:0.09

10:0.07

11:0.09

Negative Logits

erate

-3.03

Ul

-2.59

nor

-2.58

nit

-2.47

hemy

-2.46

rss

-2.44

mur

-2.43

 prosec

-2.40

}:

-2.39

ourning

-2.38

POSITIVE LOGITS

 Bought

3.27

 Came

2.72

 Barkley

2.65

 Sapphire

2.64

 powd

2.62

 Spiel

2.60

 charms

2.59

Spo

2.56

Newsletter

2.51

 Cards

2.47

Activations Density 0.000%

references to physical locations or structures

No Comments

No Known Activations