INDEX

Explanations

connections and relationships involving "domestic" and related terms in various contexts

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

0:0.04

1:0.14

2:0.04

3:0.11

4:0.07

5:0.02

6:0.06

7:0.31

8:0.02

9:0.03

10:0.06

11:0.07

Negative Logits

 glim

-2.19

 psychiat

-2.16

��

-2.16

veyard

-2.10

onda

-2.07

urban

-2.03

mary

-2.02

anton

-2.02

affected

-1.99

MD

-1.99

POSITIVE LOGITS

�

2.85

 Goku

2.57

Kak

2.31

�

2.22

</

2.04

 Luffy

2.00

 Lopez

1.99

DoS

1.95

Tos

1.94

 Kham

1.93

Activations Density 0.003%

connections and relationships involving "domestic" and related terms in various contexts

No Comments

No Known Activations