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

1:0.09

2:0.09

3:0.08

4:0.09

5:0.07

6:0.08

7:0.07

8:0.09

9:0.06

10:0.07

11:0.08

Negative Logits

Shop

-1.59

 Gujar

-1.59

RBI

-1.47

 Fiat

-1.46

CBI

-1.37

Exception

-1.36

 Yamaha

-1.36

Helper

-1.34

oubted

-1.33

 Mean

-1.32

POSITIVE LOGITS

achus

1.96

 Aires

1.68

insula

1.63

istan

1.63

adelphia

1.63

ipel

1.61

thia

1.60

 looph

1.59

qqa

1.59

abul

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.