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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.10

8:0.07

9:0.07

10:0.07

11:0.07

Negative Logits

fut

-2.51

 props

-2.43

 fret

-2.36

 autop

-2.35

 Thought

-2.33

 Bing

-2.25

 vacuum

-2.20

 tips

-2.13

advertisement

-2.12

 vibr

-2.10

POSITIVE LOGITS

hoe

2.68

uilt

2.52

ocene

2.44

eteria

2.43

onite

2.41

orthern

2.37

abwe

2.37

isSpecialOrderable

2.34

lik

2.32

lvl

2.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.