INDEX

Explanations

situations involving emotional responses or significant events related to personal experiences

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

0:0.29

1:0.09

2:0.08

3:0.04

4:0.07

5:0.02

6:0.07

7:0.07

8:0.02

9:0.03

10:0.11

11:0.06

Negative Logits

aeper

-4.82

Assad

-4.12

Wilson

-4.07

utsche

-3.93

 Wilson

-3.66

 Syrians

-3.60

houn

-3.51

Syria

-3.49

 Kaepernick

-3.47

vironment

-3.42

POSITIVE LOGITS

 Magic

9.68

Magic

9.03

magic

7.75

 magic

7.64

 magician

7.57

 Magical

7.01

 mages

6.81

 wizards

6.68

 Mages

6.63

 mage

6.44

Activations Density 0.048%

situations involving emotional responses or significant events related to personal experiences

No Comments

No Known Activations