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

1:0.08

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

 Anat

-2.75

 Plastic

-2.67

 Parenthood

-2.66

 Drawn

-2.52

 Worm

-2.51

 Atom

-2.50

Bot

-2.49

 Vessel

-2.49

 anth

-2.48

 Uzbek

-2.43

POSITIVE LOGITS

isSpecialOrderable

3.99

taboola

3.55

alks

2.77

[/

2.62

quickShipAvailable

2.59

soType

2.59

HUD

2.56

lance

2.56

deb

2.55

></

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.