INDEX

Explanations

actions or movements involving competition or races

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

2:0.06

3:0.13

4:0.02

5:0.04

6:0.04

7:0.08

8:0.07

9:0.33

10:0.05

11:0.07

Negative Logits

sent

-1.49

SPONSORED

-1.45

ointment

-1.34

notations

-1.31

chant

-1.31

claimer

-1.25

watching

-1.24

notation

-1.23

ב

-1.18

cit

-1.18

POSITIVE LOGITS

 Waterloo

1.48

 unbeaten

1.41

 undefeated

1.34

ifferent

1.21

utenberg

1.19

 competing

1.19

 unification

1.18

 progressively

1.18

ulators

1.17

 McMaster

1.15

Activations Density 0.008%

actions or movements involving competition or races

No Comments

No Known Activations