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

0:0.10

1:0.08

2:0.10

3:0.08

4:0.07

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.07

11:0.09

Negative Logits

 hobby

-2.82

 rotating

-2.67

 puppet

-2.67

 budgetary

-2.59

 barg

-2.56

 revolving

-2.54

brow

-2.50

 newsletters

-2.44

catentry

-2.40

 drag

-2.40

POSITIVE LOGITS

Tes

3.02

MIT

2.73

CBC

2.64

NZ

2.58

 Diabetes

2.58

 Radeon

2.51

Tesla

2.50

[/

2.49

buquerque

2.46

EPA

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.