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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.06

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Nep

-1.53

 Leap

-1.49

wine

-1.47

 Monte

-1.46

sov

-1.44

 commun

-1.42

 diagnosis

-1.40

Doctors

-1.38

 Chronic

-1.37

orc

-1.36

POSITIVE LOGITS

ONSORED

1.70

_-

1.61

ike

1.53

zilla

1.52

alos

1.51

orative

1.48

"}

1.47

 congratulate

1.47

ilial

1.46

govtrack

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.