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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.10

8:0.06

9:0.08

10:0.09

11:0.08

Negative Logits

collect

-2.75

Torrent

-2.66

 traveller

-2.57

 Colony

-2.57

 Destination

-2.55

 Toll

-2.54

 Squadron

-2.51

verse

-2.49

 Dimension

-2.46

iversal

-2.41

POSITIVE LOGITS

anyahu

2.64

yang

2.62

�

2.62

 fiat

2.58

龍�

2.55

サ

2.47

 Obama

2.42

ilitary

2.41

jew

2.41

skirts

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.