INDEX

Explanations

expressions of change, particularly those that quantify increases or shifts in conditions or situations

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

0:0.05

1:0.03

2:0.04

3:0.13

4:0.03

5:0.07

6:0.04

7:0.09

8:0.05

9:0.02

10:0.36

11:0.04

Negative Logits

 before

-3.05

 despite

-3.01

 until

-3.00

 after

-2.99

 while

-2.93

 whilst

-2.89

 ahead

-2.78

 during

-2.77

 onto

-2.76

 towards

-2.73

POSITIVE LOGITS

DragonMagazine

2.82

Fax

2.44

Dialogue

2.38

iox

2.29

arthy

2.28

tumblr

2.27

rocal

2.17

latable

2.17

pty

2.16

opus

2.13

Activations Density 0.005%

expressions of change, particularly those that quantify increases or shifts in conditions or situations

No Comments

No Known Activations