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

0:0.09

1:0.07

2:0.09

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

Task

-3.07

asks

-2.66

 missions

-2.61

 Crowley

-2.60

obos

-2.55

Rogue

-2.53

amins

-2.50

 gifts

-2.50

Pool

-2.48

Minecraft

-2.47

POSITIVE LOGITS

 eleph

3.02

ERA

2.77

 hypert

2.70

 lever

2.65

ariat

2.63

∼

2.58

 coronary

2.57

 actu

2.57

)—

2.56

 rupture

2.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.