INDEX

Explanations

references to subscriptions and the latest issues from a publication

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

0:0.20

1:0.01

2:0.10

3:0.08

4:0.04

5:0.09

6:0.12

7:0.08

8:0.10

9:0.02

10:0.09

11:0.02

Negative Logits

 therapists

-2.69

 wheelchair

-2.65

 Chun

-2.60

Plex

-2.59

 mirrors

-2.53

NEC

-2.51

 auditor

-2.49

 Canaver

-2.48

gym

-2.48

 Brighton

-2.47

POSITIVE LOGITS

 Travels

2.60

redo

2.54

 Savage

2.48

ilege

2.36

 Province

2.35

 Sovere

2.33

 Doomsday

2.31

eatured

2.29

 Massacre

2.28

athering

2.28

Activations Density 0.005%

references to subscriptions and the latest issues from a publication

No Comments

No Known Activations