INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.08

1:0.07

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

maxwell

-2.67

 dodge

-2.65

ITNESS

-2.61

 Scion

-2.61

 Fraz

-2.50

 melee

-2.49

 artery

-2.43

actionDate

-2.43

━

-2.42

 Cout

-2.40

POSITIVE LOGITS

GV

2.53

CN

2.52

WW

2.38

owder

2.34

bm

2.32

 Weekly

2.30

:[

2.26

pling

2.24

WH

2.24

gt

2.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.