INDEX

Explanations

pharmaceutical drug names and medical conditions related to bones and joints

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to specific drugs and their medical effects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

0:0.10

1:0.04

2:0.18

3:0.06

4:0.11

5:0.07

6:0.04

7:0.04

8:0.04

9:0.15

10:0.07

11:0.04

Negative Logits

pse

-1.41

ISI

-1.26

alyses

-1.18

 Hawai

-1.17

 Tayyip

-1.14

 cues

-1.13

itored

-1.12

viz

-1.09

icators

-1.09

 Kissinger

-1.08

POSITIVE LOGITS

nova

1.31

arnaev

1.30

schild

1.28

ajo

1.22

boa

1.21

atform

1.20

ashtra

1.19

nov

1.18

adesh

1.17

merce

1.17

Activations Density 0.001%

pharmaceutical drug names and medical conditions related to bones and joints

references to specific drugs and their medical effects

No Comments

No Known Activations