INDEX

Explanations

keywords indicating frequency or quantity

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

2:0.17

3:0.08

4:0.14

5:0.03

6:0.02

7:0.29

8:0.03

9:0.03

10:0.05

11:0.08

Negative Logits

crime

-1.36

erity

-1.34

ativity

-1.33

enhagen

-1.33

stros

-1.31

cia

-1.31

Marginal

-1.30

arie

-1.30

rection

-1.30

ioch

-1.30

POSITIVE LOGITS

 disclaim

1.61

[|

1.45

 Vend

1.24

 horm

1.23

 Hipp

1.18

 wont

1.17

bet

1.17

 Beware

1.17

 expect

1.16

birds

1.16

Activations Density 0.007%

keywords indicating frequency or quantity

No Comments

No Known Activations