INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

DragonMagazine

-1.99

anguages

-1.94

yrim

-1.93

inav

-1.90

conom

-1.85

arel

-1.85

Ott

-1.81

ocaly

-1.78

apons

-1.78

assetsadobe

-1.76

POSITIVE LOGITS

 steam

1.64

 affirmation

1.58

ModLoader

1.52

 affirmative

1.49

 silence

1.47

 fuse

1.46

 implication

1.46

 backwards

1.44

CHAT

1.43

 unknown

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.