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

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.06

7:0.08

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

 Beir

-1.93

 Cassidy

-1.80

NP

-1.52

 Wolfe

-1.50

ASA

-1.48

 interviewer

-1.45

CHR

-1.43

 Marine

-1.43

ofer

-1.43

 incendiary

-1.43

POSITIVE LOGITS

Interstitial

2.21

ween

1.88

vern

1.83

ixel

1.79

eways

1.79

VERTISEMENT

1.78

cius

1.72

 routines

1.69

din

1.64

��

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.