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

3:0.09

4:0.08

5:0.08

6:0.06

7:0.07

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

FF

-3.60

 Submission

-2.90

ABS

-2.62

 Patreon

-2.54

RN

-2.43

END

-2.42

 LIVE

-2.41

SF

-2.31

Δ

-2.29

PID

-2.27

POSITIVE LOGITS

hower

2.95

TRUMP

2.95

Malley

2.95

 Muller

2.73

 Schwe

2.64

Bush

2.64

Flor

2.50

Louis

2.46

 Chaff

2.46

aund

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.