INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.06

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 fertil

-1.58

fal

-1.56

 ammon

-1.55

 licence

-1.51

 practise

-1.44

ndum

-1.43

 stagn

-1.42

arf

-1.41

uka

-1.40

 stake

-1.39

POSITIVE LOGITS

edIn

1.98

CLASS

1.78

oples

1.72

ovych

1.70

leck

1.65

 Rouge

1.62

arthed

1.59

HUD

1.58

-+-+

1.55

��

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.