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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

 superior

-1.80

 comb

-1.66

 Discipline

-1.64

 suppressing

-1.63

entin

-1.61

 exposing

-1.58

idi

-1.54

 identifying

-1.53

ascript

-1.52

 Enhancement

-1.51

POSITIVE LOGITS

abal

2.19

 Roose

1.88

soDeliveryDate

1.86

Gaz

1.72

 sshd

1.70

 tragedies

1.68

oglu

1.67

Kal

1.64

heit

1.61

 裏�

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.