INDEX

Explanations

references to events or gatherings and their organizational aspects

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.06

2:0.06

3:0.04

4:0.02

5:0.03

6:0.10

7:0.14

8:0.02

9:0.03

10:0.22

11:0.03

Negative Logits

 Aden

-3.97

 Leviathan

-3.93

 Maharashtra

-3.20

izabeth

-2.97

 Sana

-2.82

 Payton

-2.74

 Ethiop

-2.71

 Koran

-2.70

 Yamato

-2.67

 Malays

-2.64

POSITIVE LOGITS

CU

9.51

CU

8.56

cu

4.51

 Boulder

4.32

UCS

3.94

Cu

3.84

 cocoa

3.57

Tu

3.54

Cu

3.52

Cub

3.44

Activations Density 0.005%

references to events or gatherings and their organizational aspects

No Comments

No Known Activations