INDEX

Explanations

references to claims or allegations regarding deception or misinformation

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

0:0.16

1:0.03

2:0.09

3:0.04

4:0.04

5:0.05

6:0.15

7:0.04

8:0.06

9:0.23

10:0.03

11:0.03

Negative Logits

acco

-3.53

Hik

-3.31

zech

-3.29

 crim

-3.24

coh

-3.23

HK

-3.22

Ic

-3.18

 Cooper

-3.17

ongh

-3.17

iolet

-3.17

POSITIVE LOGITS

 Rend

8.89

Render

8.22

 Render

8.00

render

7.47

 render

7.36

 rendering

7.25

rendered

6.53

 rend

6.38

 rendered

6.10

 renders

6.07

Activations Density 0.001%

references to claims or allegations regarding deception or misinformation

No Comments

No Known Activations