INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

3:0.08

4:0.08

5:0.09

6:0.06

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

elsen

-2.83

MSN

-2.75

loc

-2.49

 commuting

-2.49

trak

-2.48

 estimates

-2.46

SI

-2.45

wi

-2.44

 negatives

-2.43

 slides

-2.40

POSITIVE LOGITS

 Flavoring

3.29

 Ancients

2.96

 Vend

2.92

 Nebula

2.85

 Orche

2.85

afort

2.73

 Designs

2.72

 Debate

2.67

 Judges

2.65

obook

2.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.