INDEX

Explanations

elements related to causative factors and effects in scientific 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

0:0.24

1:0.05

2:0.08

3:0.05

4:0.06

5:0.03

6:0.10

7:0.07

8:0.02

9:0.05

10:0.12

11:0.08

Negative Logits

illard

-3.62

 Schwar

-3.48

venant

-3.45

 Bever

-3.42

 Steph

-3.39

Bru

-3.35

pkg

-3.25

 Covenant

-3.15

 lamb

-3.14

 Malone

-3.11

POSITIVE LOGITS

DCS

7.87

 electrode

5.73

 electrodes

5.69

EEG

5.28

 stimulation

5.16

 stim

4.92

 electro

4.68

 Stim

4.55

 ADHD

4.39

DC

4.23

Activations Density 0.002%

elements related to causative factors and effects in scientific contexts

No Comments

No Known Activations