INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.07

2:0.07

3:0.08

4:0.07

5:0.07

6:0.08

7:0.09

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

NET

-1.47

YC

-1.31

 Chennai

-1.25

 counterparts

-1.25

idays

-1.24

agonists

-1.23

RAW

-1.22

FS

-1.22

ots

-1.20

◼

-1.20

POSITIVE LOGITS

dit

1.63

letal

1.59

 Canaver

1.50

abis

1.44

payer

1.43

rius

1.36

Wallet

1.36

geon

1.33

duc

1.33

brush

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.