INDEX

Explanations

information related to muscles, muscle cramping, fatigue, and muscle tissue repair

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

terms related to muscle condition and injuries

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

0:0.05

1:0.04

2:0.23

3:0.06

4:0.10

5:0.07

6:0.02

7:0.03

8:0.05

9:0.20

10:0.05

11:0.03

Negative Logits

 Nationwide

-1.24

 Grounds

-1.21

nob

-1.21

Mub

-1.18

 Criminal

-1.17

 Tradable

-1.17

Guest

-1.15

 Policies

-1.14

license

-1.14

 Forgotten

-1.13

POSITIVE LOGITS

ngth

1.48

cone

1.35

 muscles

1.34

unct

1.29

cles

1.27

rients

1.25

 tendon

1.25

 secretion

1.22

 athleticism

1.21

twitch

1.20

Activations Density 0.009%

information related to muscles, muscle cramping, fatigue, and muscle tissue repair

terms related to muscle condition and injuries

No Comments

No Known Activations