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

0:0.13

1:0.11

2:0.08

3:0.07

4:0.06

5:0.06

6:0.08

7:0.06

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Nich

-1.66

Rog

-1.63

Ki

-1.63

 Seym

-1.60

 Werner

-1.58

PHI

-1.58

 Mellon

-1.56

 Ezra

-1.54

renheit

-1.53

 Jeffrey

-1.52

POSITIVE LOGITS

advertising

1.66

 importing

1.65

 exporting

1.55

 cloning

1.53

 slaughter

1.51

 proven

1.50

 Restrict

1.44

 crest

1.43

 transpl

1.43

****************

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.