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

1:0.06

2:0.08

3:0.07

4:0.07

5:0.09

6:0.07

7:0.09

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

anges

-1.57

ezvous

-1.53

 cohesion

-1.51

 depends

-1.51

iqueness

-1.50

TPPStreamerBot

-1.48

 Relationship

-1.47

Learning

-1.46

Function

-1.44

aughs

-1.43

POSITIVE LOGITS

 undisclosed

1.76

Winged

1.64

 Fenrir

1.63

uchin

1.59

ozo

1.45

�

1.43

yne

1.42

zan

1.37

 Kuro

1.37

Nug

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.