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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

Bos

-2.64

teness

-2.54

cision

-2.53

minster

-2.52

Sri

-2.49

ospace

-2.46

atro

-2.45

 semic

-2.44

Cer

-2.37

 Shim

-2.36

POSITIVE LOGITS

Buy

2.70

 Medicaid

2.32

 vend

2.29

Connect

2.28

mix

2.27

Lex

2.25

 feral

2.25

 Texans

2.25

 Defenders

2.24

 Fitz

2.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.