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

0:0.09

1:0.07

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

ilial

-3.20

 Loans

-2.98

ipal

-2.82

ospons

-2.79

irrel

-2.78

 --------

-2.75

orrow

-2.71

 colle

-2.69

 sidx

-2.69

lement

-2.63

POSITIVE LOGITS

 biome

2.91

 durability

2.52

 encyclopedia

2.39

UX

2.39

 scoreboard

2.35

 poppy

2.33

YP

2.29

Wo

2.28

och

2.27

 whales

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.