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

1:0.07

2:0.08

3:0.07

4:0.07

5:0.09

6:0.09

7:0.07

8:0.09

9:0.07

10:0.09

11:0.08

Negative Logits

mble

-1.82

izu

-1.58

pled

-1.56

gow

-1.52

ribe

-1.51

naire

-1.49

ño

-1.48

nce

-1.47

 torches

-1.45

clusion

-1.45

POSITIVE LOGITS

機

2.05

 proble

1.75

 Statistics

1.69

 Costs

1.66

ccording

1.65

 Cannot

1.59

BuyableInstoreAndOnline

1.56

 Purg

1.55

ANG

1.55

 arithmetic

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.