INDEX

Explanations

references to regulatory or legal processes

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

0:0.06

1:0.41

2:0.05

3:0.04

4:0.03

5:0.02

6:0.05

7:0.09

8:0.03

9:0.03

10:0.10

11:0.04

Negative Logits

 Chest

-2.62

 Frie

-2.62

 empt

-2.42

Uri

-2.40

 arom

-2.39

 Brist

-2.38

tsy

-2.37

 Fall

-2.36

Iv

-2.32

 Blossom

-2.29

POSITIVE LOGITS

Super

8.20

 Super

7.90

super

7.86

 super

7.84

 SUPER

6.57

uper

4.46

Sup

4.43

 supers

4.28

SUP

4.28

Ultra

4.18

Activations Density 0.117%

references to regulatory or legal processes

No Comments

No Known Activations