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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

EEG

-3.04

Putin

-2.85

�

-2.83

chuk

-2.73

araoh

-2.71

iak

-2.70

 Putin

-2.67

byter

-2.66

omsky

-2.65

ichick

-2.63

POSITIVE LOGITS

 Dublin

2.71

 Maiden

2.61

 dear

2.60

 Lord

2.56

 Flavoring

2.55

wen

2.55

letter

2.52

 Winchester

2.49

 Lords

2.43

 Wick

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.