INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.06

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.10

Negative Logits

 Gale

-1.42

assies

-1.40

 peace

-1.32

braska

-1.30

ccess

-1.30

 Patrol

-1.30

psons

-1.27

 Owens

-1.27

 delegate

-1.25

legates

-1.23

POSITIVE LOGITS

 WATCHED

2.00

esian

1.87

_-

1.54

cry

1.46

yout

1.44

 Minotaur

1.39

═

1.36

_>

1.33

 Interstellar

1.33

 DRAGON

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.