INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.09

2:0.07

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 acknow

-2.27

 proble

-2.13

 Baghd

-2.05

wu

-1.86

yi

-1.85

 CODE

-1.83

 agre

-1.81

 SECTION

-1.80

 conclud

-1.79

oğ

-1.79

POSITIVE LOGITS

animate

1.80

ensity

1.69

living

1.64

hire

1.61

olls

1.61

hers

1.55

neutral

1.52

exper

1.52

elson

1.51

 magnet

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.