INDEX

Explanations

frequent mentions of the word "the" and related high-frequency pronouns and articles

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.01

2:0.08

3:0.10

4:0.14

5:0.04

6:0.18

7:0.15

8:0.04

9:0.06

10:0.08

11:0.05

Negative Logits

ategories

-1.54

 Cosponsors

-1.51

<<

-1.46

":"

-1.46

htaking

-1.44

SQL

-1.42

quer

-1.38

ベ

-1.37

outh

-1.35

rimp

-1.34

POSITIVE LOGITS

 expires

1.61

 recess

1.51

Nev

1.45

 transmissions

1.44

 litigation

1.39

ogene

1.38

 licens

1.35

 Herz

1.30

irement

1.24

 deliberations

1.24

Activations Density 0.001%

frequent mentions of the word "the" and related high-frequency pronouns and articles

No Comments

No Known Activations