INDEX

Explanations

phrases related to injury updates and recovery in sports contexts

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.22

1:0.10

2:0.04

3:0.03

4:0.03

5:0.02

6:0.14

7:0.11

8:0.03

9:0.03

10:0.16

11:0.04

Negative Logits

 Lois

-3.68

 Huawei

-3.50

 Briggs

-3.36

QC

-3.06

Jud

-3.02

atel

-3.00

 miner

-2.98

 Yosemite

-2.96

MX

-2.95

Lewis

-2.91

POSITIVE LOGITS

Spo

8.18

 Bosh

4.11

 Granger

3.92

 Bucs

3.72

 Tampa

3.58

angelo

3.53

Dw

3.45

 Erik

3.42

 Heat

3.32

 Florida

3.23

Activations Density 0.001%

phrases related to injury updates and recovery in sports contexts

No Comments

No Known Activations