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

0:0.05

1:0.11

2:0.08

3:0.08

4:0.10

5:0.07

6:0.06

7:0.10

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

 Maxim

-1.84

Wiz

-1.74

 Create

-1.56

 Pens

-1.49

Nex

-1.48

 Perform

-1.48

 Discover

-1.47

Dur

-1.46

VK

-1.45

 Wizards

-1.45

POSITIVE LOGITS

lees

1.80

edes

1.65

frog

1.59

AAAA

1.58

 outnumbered

1.54

ymes

1.53

..............

1.52

ospels

1.52

psons

1.52

league

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.