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

1:0.06

2:0.07

3:0.09

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 moot

-2.12

 Cassidy

-1.80

 outweigh

-1.61

 Loving

-1.60

 Buddhism

-1.60

 Hurt

-1.59

 Voting

-1.58

 Abrams

-1.58

ihilation

-1.54

 Renew

-1.51

POSITIVE LOGITS

bda

2.00

common

1.86

ECD

1.85

stretched

1.84

doi

1.83

udeb

1.78

Python

1.75

typically

1.75

usually

1.75

{"

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.