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

1:0.09

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.06

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 implants

-1.72

aspers

-1.70

�

-1.59

mbuds

-1.58

 spark

-1.55

inkle

-1.48

oufl

-1.44

rooms

-1.43

xy

-1.42

っ

-1.41

POSITIVE LOGITS

dayName

1.78

 converge

1.61

 ORDER

1.57

 Appropriations

1.56

+/-

1.43

 wont

1.42

externalActionCode

1.42

 mins

1.40

mins

1.40

deen

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.