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

0:0.07

1:0.11

2:0.08

3:0.09

4:0.07

5:0.07

6:0.08

7:0.07

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

 editors

-2.03

omorphic

-1.89

 Editors

-1.85

 GNOME

-1.82

alks

-1.77

 Haskell

-1.75

ibli

-1.73

clusions

-1.73

 Hats

-1.64

omas

-1.63

POSITIVE LOGITS

 payable

1.78

wcs

1.75

EStreamFrame

1.68

elsius

1.67

 Oval

1.66

Physical

1.58

 initiating

1.51

 initiation

1.48

 furnace

1.45

 mirror

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.