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

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.09

11:0.09

Negative Logits

SourceFile

-2.06

abases

-1.93

═

-1.77

rendered

-1.73

Marvel

-1.69

�

-1.68

saf

-1.68

�

-1.67

abase

-1.63

��

-1.62

POSITIVE LOGITS

 overt

1.68

)",

1.61

vity

1.56

 arithmetic

1.53

Ö

1.52

abal

1.47

Iz

1.45

GG

1.45

Baz

1.43

)"

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.