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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

£

-3.04

£

-2.87

 Wrestling

-2.66

=>

-2.66

 Labour

-2.58

 Advertising

-2.48

Labour

-2.46

 Supply

-2.42

 Count

-2.40

 Patient

-2.35

POSITIVE LOGITS

cients

2.73

artifacts

2.63

 coff

2.63

arij

2.61

quished

2.53

 ashes

2.51

 artifact

2.50

 scorp

2.48

eport

2.48

 departed

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.