INDEX

Explanations

references to older demographics and their related issues

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

2:0.08

3:0.07

4:0.01

5:0.04

6:0.17

7:0.14

8:0.04

9:0.02

10:0.06

11:0.27

Negative Logits

-1.22

azard

-1.18

arity

-1.12

ihilation

-1.04

rosis

-1.03

mberg

-1.02

atility

-1.01

adesh

-0.98

afety

-0.96

assador

-0.95

POSITIVE LOGITS

than

2.32

 than

1.83

 Than

1.58

 wiser

1.23

models

1.13

 lapt

1.06

types

1.05

Jr

1.03

 traditions

1.02

 smoother

0.96

Activations Density 0.025%

references to older demographics and their related issues

No Comments

No Known Activations