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

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.06

8:0.10

9:0.07

10:0.09

11:0.08

Negative Logits

�醒

-1.77

 complainant

-1.60

culosis

-1.58

 plaintiff

-1.57

 defect

-1.55

eligible

-1.55

evidence

-1.51

orio

-1.51

eur

-1.48

 claimant

-1.44

POSITIVE LOGITS

Games

1.75

 Quadro

1.68

 Giles

1.61

 Pyramid

1.61

 Koen

1.59

[|

1.57

ARDIS

1.57

 Firefly

1.55

 Lent

1.54

lot

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.