INDEX

Explanations

phrases indicating actions or changes involving the word "to"

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

0:0.01

1:0.02

2:0.08

3:0.17

4:0.01

5:0.03

6:0.07

7:0.08

8:0.05

9:0.22

10:0.09

11:0.11

Negative Logits

CHAT

-1.52

ukemia

-1.32

beit

-1.25

aft

-1.20

ÃÂ

-1.19

dayName

-1.15

TIME

-1.15

Liter

-1.15

Kind

-1.14

zeb

-1.14

POSITIVE LOGITS

roth

1.36

 Inquis

1.23

 Moto

1.21

 Gaal

1.19

Osw

1.12

atars

1.10

 Plaza

1.08

 Nico

1.06

 squad

1.06

 Nare

1.05

Activations Density 0.007%

phrases indicating actions or changes involving the word "to"

No Comments

No Known Activations