INDEX

Explanations

questions that express uncertainty or seek clarification

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.02

1:0.05

2:0.15

3:0.06

4:0.01

5:0.04

6:0.13

7:0.09

8:0.20

9:0.06

10:0.08

11:0.06

Negative Logits

nil

-1.10

Champ

-1.02

 Bren

-1.00

 Gutenberg

-0.98

 opens

-0.97

yard

-0.96

 Laugh

-0.96

ilated

-0.96

yards

-0.95

mington

-0.94

POSITIVE LOGITS

 responsiveness

1.40

awaru

1.38

 behaviours

1.37

 susceptibility

1.27

 behavi

1.25

 offending

1.24

 behaviour

1.23

 perceptions

1.23

 motivations

1.18

 behav

1.18

Activations Density 0.022%

questions that express uncertainty or seek clarification

No Comments

No Known Activations