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

0:0.07

1:0.07

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

Spoiler

-1.63

 interviewing

-1.51

episode

-1.50

 skeptical

-1.48

 tuned

-1.41

???

-1.37

 interviewed

-1.35

 guesses

-1.35

ickets

-1.33

00200000

-1.31

POSITIVE LOGITS

1.72

 Confederation

1.68

senal

1.63

 Conquer

1.57

�士

1.56

 Fountain

1.51

ulkan

1.48

 Harmony

1.47

 Atom

1.46

odore

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.