INDEX

Explanations

No Explanations Found

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

0:0.08

1:0.07

2:0.07

3:0.09

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

-2.39

 Oliver

-2.26

 Jordanian

-2.23

 surgeon

-2.20

 astronaut

-2.17

 Casey

-2.16

 parachute

-2.13

 astronauts

-2.07

 anal

-2.04

 Alberto

-2.02

POSITIVE LOGITS

��極

2.84

ensibly

2.70

enhagen

2.60

Cth

2.54

senal

2.51

ヘラ

2.47

 millenn

2.44

isSpecial

2.39

 practition

2.30

Storm

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.