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

1:0.10

2:0.08

3:0.07

4:0.08

5:0.08

6:0.07

7:0.06

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

depend

-1.92

xual

-1.91

 experien

-1.89

 belie

-1.88

 nodd

-1.83

sonian

-1.83

iband

-1.80

 therap

-1.76

yg

-1.76

 crave

-1.74

POSITIVE LOGITS

 Commissioner

1.88

 Barclays

1.85

 Coliseum

1.78

 Typhoon

1.77

La

1.76

 Eddie

1.70

 Rounds

1.69

 Calder

1.69

 Windsor

1.64

 Affairs

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.