INDEX

Explanations

instances of the word "f***" in various forms within the text

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

1:0.03

2:0.08

3:0.26

4:0.02

5:0.02

6:0.05

7:0.22

8:0.07

9:0.05

10:0.07

11:0.04

Negative Logits

quickShipAvailable

-1.50

SEA

-1.41

theless

-1.34

SPA

-1.34

ItemImage

-1.32

 vantage

-1.29

ggles

-1.28

Lower

-1.24

imester

-1.24

OTA

-1.20

POSITIVE LOGITS

 scrap

1.44

 gigg

1.28

rices

1.25

ric

1.23

 bullshit

1.18

 boobs

1.18

culosis

1.15

ibaba

1.14

 scraps

1.14

 haunted

1.14

Activations Density 0.012%

instances of the word "f***" in various forms within the text

No Comments

No Known Activations