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

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.07

8:0.08

9:0.10

10:0.07

11:0.07

Negative Logits

ْ

-1.88

�

-1.82

Ranked

-1.80

estyles

-1.75

irl

-1.75

kees

-1.70

-+-+

-1.69

�

-1.67

"]=>

-1.67

�

-1.64

POSITIVE LOGITS

brand

1.98

ema

1.76

ournal

1.76

psey

1.73

 Monarch

1.65

 recess

1.63

 bean

1.49

owe

1.48

 Crane

1.48

udeau

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.