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

2:0.09

3:0.08

4:0.09

5:0.09

6:0.07

7:0.07

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

inki

-2.72

覚醒

-2.48

 circuitry

-2.48

spring

-2.43

arcer

-2.42

stim

-2.40

anke

-2.40

ilitary

-2.36

ipolar

-2.35

Econom

-2.34

POSITIVE LOGITS

Ng

2.72

Sut

2.52

 Morales

2.52

 Welch

2.51

 Willie

2.48

 Morrison

2.47

 Griffin

2.46

 shorth

2.45

Ply

2.45

Beg

2.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.