INDEX

Explanations

forward slashes

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

0:0.01

1:0.01

2:0.12

3:0.10

4:0.23

5:0.02

6:0.09

7:0.15

8:0.02

9:0.04

10:0.05

11:0.09

Negative Logits

————

-1.48

 negatives

-1.40

artifacts

-1.40

 dates

-1.39

omaly

-1.39

alach

-1.34

represented

-1.32

 Shadows

-1.32

 streaks

-1.31

profits

-1.30

POSITIVE LOGITS

bie

1.55

shock

1.44

eer

1.40

pic

1.38

ghan

1.38

itative

1.37

mom

1.32

 chuckle

1.32

MOR

1.31

izzy

1.29

Activations Density 0.003%

forward slashes

No Comments

No Known Activations