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

1:0.07

2:0.09

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

IFIED

-1.70

 ANGEL

-1.55

ONSORED

-1.52

isode

-1.40

Plot

-1.39

idable

-1.39

miah

-1.36

Course

-1.35

pects

-1.35

Discussion

-1.34

POSITIVE LOGITS

 choke

1.51

 Fist

1.41

 ASAP

1.37

ifice

1.36

 stadiums

1.28

 caps

1.23

bu

1.20

 fame

1.20

caps

1.19

cig

1.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.