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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

 GDDR

-1.90

 guiName

-1.68

 BlackBerry

-1.54

 trillions

-1.47

yen

-1.44

 Fiat

-1.43

MMO

-1.43

 Fiction

-1.41

 DEFENSE

-1.41

 Pocket

-1.40

POSITIVE LOGITS

ğ

2.10

aterasu

2.06

oğ

1.94

ilda

1.84

psey

1.77

halla

1.72

 journeys

1.69

ItemThumbnailImage

1.69

asive

1.66

skirts

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.