INDEX

Explanations

references to legal issues or copyright matters

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

0:0.02

1:0.01

2:0.12

3:0.14

4:0.23

5:0.04

6:0.15

7:0.02

8:0.04

9:0.08

10:0.06

11:0.03

Negative Logits

 Twice

-1.31

Redd

-1.26

 Restoration

-1.22

 Slater

-1.21

 waiver

-1.20

 Admission

-1.18

 Tomb

-1.18

 Three

-1.16

 Twenty

-1.16

Pur

-1.16

POSITIVE LOGITS

rael

1.58

izza

1.55

))))

1.53

andre

1.45

ui

1.41

�

1.39

oi

1.38

":{"

1.38

)))

1.37

oba

1.35

Activations Density 0.006%

references to legal issues or copyright matters

No Comments

No Known Activations