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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.07

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

Per

-1.66

Gam

-1.56

 Singh

-1.55

 Singer

-1.51

 Theft

-1.51

 owns

-1.50

mt

-1.48

Mit

-1.47

 Cond

-1.44

 Desire

-1.44

POSITIVE LOGITS

tips

1.99

odox

1.94

sembly

1.91

heast

1.90

apult

1.90

geons

1.89

leys

1.86

vote

1.85

gently

1.80

 Flavoring

1.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.