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

0:0.09

1:0.08

2:0.07

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.06

9:0.10

10:0.08

11:0.08

Negative Logits

 Nass

-2.75

 flagged

-2.62

 Maur

-2.56

 Airbus

-2.55

 Blanc

-2.54

Poc

-2.51

 Carney

-2.49

 Nico

-2.48

 Dele

-2.47

 worse

-2.46

POSITIVE LOGITS

natureconservancy

3.78

pha

2.91

xual

2.88

ovember

2.86

 DISTR

2.64

atics

2.56

oxin

2.55

 Committees

2.46

uberty

2.45

angs

2.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.