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

0:0.08

1:0.07

2:0.08

3:0.07

4:0.07

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 antiquity

-1.51

 Gleaming

-1.48

 lowly

-1.43

 fanbase

-1.37

 purity

-1.36

 bona

-1.34

 parity

-1.33

 fortunes

-1.32

 receptors

-1.28

 rivals

-1.27

POSITIVE LOGITS

ndra

1.64

ertodd

1.48

________________

1.47

iasco

1.41

 redacted

1.36

 Hasan

1.29

 Jail

1.28

 Jindal

1.28

phabet

1.26

ahn

1.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.