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

1:0.06

2:0.07

3:0.09

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

Ops

-1.94

 crashes

-1.66

 Shine

-1.57

り

-1.52

oples

-1.48

elin

-1.48

 outputs

-1.47

rones

-1.46

ocom

-1.41

Apps

-1.41

POSITIVE LOGITS

 Twain

1.69

uf

1.62

 reservations

1.58

 Maur

1.57

BuyableInstoreAndOnline

1.54

TAG

1.50

 liking

1.50

tad

1.49

 seiz

1.49

 signings

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.