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

2:0.10

3:0.07

4:0.08

5:0.07

6:0.06

7:0.10

8:0.08

9:0.06

10:0.09

11:0.10

Negative Logits

[*

-1.68

 undesirable

-1.65

 unwanted

-1.60

 suspicions

-1.59

 unwelcome

-1.58

 verifying

-1.57

 checking

-1.54

 shielding

-1.54

 disqual

-1.50

 doubted

-1.50

POSITIVE LOGITS

gency

1.95

reprene

1.81

govern

1.81

grand

1.77

artisan

1.69

vel

1.66

 Ages

1.64

ventures

1.64

thood

1.64

ranean

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.