INDEX

Explanations

occurrences of the word "up" along with phrases indicating progression or elevation

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

1:0.02

2:0.12

3:0.07

4:0.01

5:0.04

6:0.06

7:0.11

8:0.07

9:0.28

10:0.07

11:0.07

Negative Logits

ught

-1.29

pton

-1.27

──

-1.17

maxwell

-1.12

 reconstruction

-1.11

Merit

-1.10

awei

-1.08

 temperament

-1.07

displayText

-1.04

 entreprene

-1.03

POSITIVE LOGITS

の�

1.26

 Pirates

1.25

 cracks

1.22

 rooft

1.22

 Soda

1.22

Yo

1.21

 Jolly

1.21

 Gleaming

1.20

thw

1.20

 torches

1.17

Activations Density 0.009%

occurrences of the word "up" along with phrases indicating progression or elevation

No Comments

No Known Activations