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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.05

2:0.08

3:0.09

4:0.08

5:0.07

6:0.07

7:0.06

8:0.10

9:0.09

10:0.08

11:0.10

Negative Logits

 Apprentice

-1.72

 Podcast

-1.63

 Magazine

-1.59

Storm

-1.58

 Fest

-1.55

PAC

-1.52

 Petition

-1.52

DVD

-1.52

LP

-1.49

WW

-1.48

POSITIVE LOGITS

etheless

1.95

abama

1.93

 cannabin

1.78

edin

1.76

berra

1.69

gypt

1.68

aeda

1.66

 captcha

1.64

 largeDownload

1.63

blance

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.