INDEX

Explanations

terms related to minor league baseball and its structure

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

0:0.05

1:0.03

2:0.07

3:0.28

4:0.03

5:0.03

6:0.14

7:0.07

8:0.05

9:0.05

10:0.06

11:0.08

Negative Logits

wagen

-1.38

etheus

-1.36

pter

-1.17

 Canaver

-1.13

Cloud

-1.13

cloud

-1.12

ulence

-1.07

ーテ

-1.07

opian

-1.07

 sterile

-1.05

POSITIVE LOGITS

 corrections

1.33

arsity

1.31

ploma

1.26

 honors

1.22

 orient

1.22

 conversions

1.21

 penalties

1.20

uchi

1.16

etc

1.15

practice

1.14

Activations Density 0.003%

terms related to minor league baseball and its structure

No Comments

No Known Activations