INDEX

Explanations

textual elements related to dialogue and reporting of statements

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.07

1:0.04

2:0.07

3:0.07

4:0.07

5:0.06

6:0.22

7:0.06

8:0.05

9:0.15

10:0.04

11:0.05

Negative Logits

 biod

-3.50

NB

-3.41

 kernel

-3.40

 mitochond

-3.38

 trunk

-3.34

 sshd

-3.27

 Syndicate

-3.27

Sap

-3.20

 mitochondrial

-3.19

 Tanaka

-3.12

POSITIVE LOGITS

Cour

7.89

 Cour

7.70

cour

6.20

 cour

5.32

 COUR

5.28

 Cove

4.63

 cove

4.38

Jur

4.02

court

3.92

 Coul

3.70

Activations Density 0.002%

textual elements related to dialogue and reporting of statements

No Comments

No Known Activations