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

0:0.07

1:0.06

2:0.07

3:0.08

4:0.07

5:0.11

6:0.07

7:0.07

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

 trivia

-1.82

 quot

-1.78

 diam

-1.68

 appearances

-1.67

 attendance

-1.63

VERTISEMENT

-1.59

 superst

-1.58

 attractions

-1.57

 engagements

-1.57

��

-1.56

POSITIVE LOGITS

directory

1.94

rep

1.86

aylor

1.81

conserv

1.80

icol

1.79

decl

1.79

アル

1.74

覚醒

1.70

property

1.68

native

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.