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

1:0.07

2:0.08

3:0.09

4:0.06

5:0.08

6:0.07

7:0.08

8:0.09

9:0.09

10:0.07

11:0.08

Negative Logits

irst

-1.50

skirts

-1.42

rade

-1.40

 possesses

-1.36

tur

-1.36

 Commander

-1.31

 Tent

-1.29

 Tome

-1.28

Twe

-1.26

cle

-1.26

POSITIVE LOGITS

 nodd

1.62

mercial

1.56

 metic

1.50

ahoo

1.49

INESS

1.49

 pessim

1.45

ODUCT

1.43

ccording

1.43

artney

1.40

iasm

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.