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

0:0.09

1:0.08

2:0.07

3:0.08

4:0.07

5:0.06

6:0.08

7:0.09

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

ajo

-1.46

bye

-1.41

cens

-1.40

 Libre

-1.34

wright

-1.30

uk

-1.30

gro

-1.30

igers

-1.29

 pilgrims

-1.22

 volunteers

-1.22

POSITIVE LOGITS

ategories

1.55

argon

1.49

ypes

1.47

ronics

1.43

mosp

1.41

arters

1.41

initions

1.40

kees

1.38

ategory

1.37

 Concepts

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.