INDEX

Explanations

technical specifications and measurements in documentation

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

0:0.15

1:0.02

2:0.14

3:0.19

4:0.05

5:0.07

6:0.04

7:0.08

8:0.09

9:0.03

10:0.04

11:0.04

Negative Logits

 sorrow

-2.54

 mourn

-2.41

iquette

-2.40

 grieving

-2.36

 etiquette

-2.35

 depl

-2.34

 revel

-2.33

 mindful

-2.32

 solemn

-2.31

hearted

-2.31

POSITIVE LOGITS

RX

3.62

MX

3.50

 Plasma

3.35

DAC

3.18

TX

3.17

AX

3.16

ADS

3.13

LD

3.13

EPS

3.03

 Specifications

3.03

Activations Density 0.516%

technical specifications and measurements in documentation

No Comments

No Known Activations