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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.09

3:0.06

4:0.09

5:0.09

6:0.08

7:0.07

8:0.09

9:0.07

10:0.10

11:0.07

Negative Logits

ilet

-1.73

iets

-1.72

¯

-1.71

sembly

-1.70

 Tycoon

-1.68

ollo

-1.66

ronics

-1.64

��

-1.62

adies

-1.62

bernatorial

-1.58

POSITIVE LOGITS

 spark

1.58

ディ

1.53

lighting

1.45

lights

1.43

 blueprint

1.42

 fragment

1.42

 amplify

1.42

 wavelength

1.35

 neoc

1.33

 ideal

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.