INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.08

2:0.09

3:0.08

4:0.06

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 partName

-2.83

 Peer

-2.64

nc

-2.46

 lobbyist

-2.39

 Publications

-2.37

otiation

-2.37

 elbows

-2.37

 lawy

-2.35

 CrossRef

-2.35

adv

-2.32

POSITIVE LOGITS

 coma

2.91

 Nero

2.81

roid

2.60

 prematurely

2.58

Sul

2.45

 epile

2.42

 redeemed

2.40

rarily

2.33

odiac

2.30

PSP

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.