INDEX

Explanations

phrases indicating belief or support for various concepts or theories

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

2:0.06

3:0.08

4:0.10

5:0.02

6:0.04

7:0.39

8:0.03

9:0.04

10:0.07

11:0.08

Negative Logits

iae

-1.70

roximately

-1.64

igmatic

-1.59

iless

-1.56

uckles

-1.54

ô

-1.48

loo

-1.48

roid

-1.46

quished

-1.45

bourg

-1.44

POSITIVE LOGITS

 orthodoxy

1.82

 recogn

1.52

 nationalism

1.50

 belief

1.46

 authenticity

1.45

 optimism

1.45

clus

1.42

 mythology

1.42

 myths

1.42

 modesty

1.41

Activations Density 0.001%

phrases indicating belief or support for various concepts or theories

No Comments

No Known Activations