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

1:0.05

2:0.08

3:0.07

4:0.09

5:0.07

6:0.08

7:0.09

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

 vacuum

-1.62

fill

-1.41

gravity

-1.39

Yog

-1.36

 Miracle

-1.33

�醒

-1.32

 Feld

-1.31

 multiply

-1.31

 void

-1.31

repeat

-1.29

POSITIVE LOGITS

vre

1.75

iott

1.69

arthed

1.60

rehensive

1.55

elligence

1.53

reviewed

1.47

 recommendation

1.46

 recommending

1.45

Acknowled

1.45

MN

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.