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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.09

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Arabic

-1.83

 melted

-1.75

 contamin

-1.65

ube

-1.62

 obscured

-1.58

mol

-1.58

 intercepted

-1.57

 saturated

-1.55

 sulf

-1.54

 typo

-1.53

POSITIVE LOGITS

OPLE

2.40

Reward

2.12

Justice

2.03

mbuds

1.89

 autonomy

1.84

bryce

1.79

Commerce

1.78

ankind

1.75

覚醒

1.73

Sov

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.