INDEX

Explanations

statements about expectations and beliefs regarding events

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.05

1:0.02

2:0.04

3:0.03

4:0.07

5:0.04

6:0.22

7:0.08

8:0.12

9:0.21

10:0.02

11:0.05

Negative Logits

 landsl

-3.94

Tree

-3.66

minster

-3.33

natureconservancy

-3.29

olesc

-3.28

 forestry

-3.26

 subst

-3.18

 sett

-3.17

Els

-3.13

tree

-3.09

POSITIVE LOGITS

 McGregor

10.26

 Conor

7.26

 Diaz

6.66

 Mayweather

5.46

 Dana

5.42

UFC

5.17

UFC

5.15

Mc

4.87

 Manny

4.80

 MacDonald

4.73

Activations Density 0.002%

statements about expectations and beliefs regarding events

No Comments

No Known Activations