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

2:0.08

3:0.08

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 worm

-2.59

 Warning

-2.52

 prope

-2.48

UFO

-2.35

rils

-2.35

minster

-2.32

azard

-2.30

stration

-2.29

 Ender

-2.27

overe

-2.27

POSITIVE LOGITS

aepernick

2.79

agher

2.58

zsche

2.52

ierrez

2.50

 Shal

2.49

isine

2.45

 Croat

2.42

ğ

2.33

 photographers

2.29

 Garc

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.