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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.07

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

ayne

-3.54

quickShipAvailable

-3.25

emouth

-3.15

isSpecialOrderable

-3.07

 Spaces

-3.04

 Isles

-3.03

Scan

-2.90

 Fisheries

-2.83

 Destination

-2.79

 Northwest

-2.77

POSITIVE LOGITS

ataka

2.52

 boxer

2.51

 historian

2.44

bre

2.41

 rapist

2.38

aceous

2.34

 induction

2.32

uctor

2.30

 prol

2.29

 rabbi

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.