INDEX

Explanations

multiple forms of the word "ballad" and its variations in different contexts

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.06

1:0.02

2:0.25

3:0.03

4:0.27

5:0.04

6:0.02

7:0.02

8:0.08

9:0.10

10:0.04

11:0.02

Negative Logits

pert

-1.45

ahime

-1.37

prise

-1.35

ULE

-1.29

advertising

-1.28

OTOS

-1.26

SQL

-1.25

TPP

-1.24

riott

-1.24

existent

-1.23

POSITIVE LOGITS

otomy

1.31

zona

1.30

icles

1.29

pus

1.29

ouver

1.27

rett

1.27

aneers

1.26

 BALL

1.25

ody

1.24

 brush

1.23

Activations Density 0.005%

multiple forms of the word "ballad" and its variations in different contexts

No Comments

No Known Activations