INDEX

Explanations

references to law enforcement or official action

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

0:0.07

1:0.09

2:0.07

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.04

9:0.10

10:0.12

11:0.07

Negative Logits

 lacks

-2.44

has

-2.43

 stretches

-2.39

 redeemed

-2.39

 extends

-2.36

 hasn

-2.36

 possesses

-2.34

 freezes

-2.34

 gathers

-2.26

 resides

-2.25

POSITIVE LOGITS

KO

2.70

 dstg

2.62

bernatorial

2.48

 Priebus

2.46

ractor

2.39

 interviewer

2.39

Coach

2.38

ilial

2.37

 announ

2.35

oultry

2.34

Activations Density 0.000%

references to law enforcement or official action

No Comments

No Known Activations