INDEX

Explanations

phrases related to personal allegations and public perception

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

0:0.08

1:0.03

2:0.05

3:0.05

4:0.04

5:0.03

6:0.24

7:0.04

8:0.07

9:0.29

10:0.02

11:0.02

Negative Logits

 Prism

-3.53

 platinum

-3.44

 livestream

-3.37

Neal

-3.36

raft

-3.35

 Columbia

-3.28

 churn

-3.26

 Borg

-3.22

 disqual

-3.19

 raft

-3.17

POSITIVE LOGITS

 Danny

9.57

Danny

9.32

 Jarvis

4.42

 Doodle

3.94

 Rosenthal

3.93

 Amend

3.90

YD

3.85

dar

3.82

Dan

3.77

 Shad

3.67

Activations Density 0.003%

phrases related to personal allegations and public perception

No Comments

No Known Activations