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

0:0.07

1:0.09

2:0.09

3:0.08

4:0.10

5:0.08

6:0.08

7:0.06

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

ylum

-1.51

asca

-1.41

accompanied

-1.40

oots

-1.35

 prest

-1.31

alin

-1.30

illes

-1.29

�

-1.28

ディ

-1.26

assic

-1.24

POSITIVE LOGITS

ktop

1.43

RIPT

1.39

arcity

1.34

soType

1.32

inventoryQuantity

1.30

oulos

1.28

ocious

1.25

scription

1.24

phabet

1.24

ITCH

1.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.