INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

complex

-3.06

Chel

-2.79

 rotor

-2.70

 loader

-2.69

iosyncr

-2.66

 overload

-2.64

 Complex

-2.63

Mech

-2.62

Lua

-2.53

Lua

-2.53

POSITIVE LOGITS

 DACA

3.41

erity

2.81

ude

2.73

 PRESIDENT

2.69

amate

2.65

AFP

2.64

ayed

2.55

OSE

2.55

 Dism

2.52

 partName

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.