INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.08

2:0.09

3:0.07

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 Canadian

-1.39

Canadian

-1.37

 Tommy

-1.36

 surg

-1.30

 British

-1.27

 Kinn

-1.27

ORN

-1.26

APTER

-1.26

ADA

-1.25

RFC

-1.25

POSITIVE LOGITS

olate

1.92

ersion

1.52

perse

1.48

antry

1.48

azo

1.45

ilon

1.44

ols

1.44

olk

1.44

arya

1.44

umenthal

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.