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

1:0.06

2:0.08

3:0.09

4:0.08

5:0.10

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 Brach

-1.49

 Abrams

-1.49

 intrig

-1.48

orthy

-1.48

 indisc

-1.43

 advances

-1.41

 Brill

-1.39

orius

-1.38

 spoiler

-1.36

Iv

-1.36

POSITIVE LOGITS

usa

1.73

auri

1.65

da

1.58

Northern

1.56

Phone

1.53

س

1.51

AIR

1.50

wx

1.47

gob

1.47

trak

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.