INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.10

2:0.08

3:0.09

4:0.08

5:0.06

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

enta

-1.57

atche

-1.48

rawdownloadcloneembedreportprint

-1.37

 counseling

-1.35

ensed

-1.35

saf

-1.34

onday

-1.32

lly

-1.31

idences

-1.31

onom

-1.30

POSITIVE LOGITS

Sao

1.74

 Johannes

1.70

 Lange

1.56

Ti

1.51

Vij

1.50

Ci

1.49

Cao

1.47

 Stephan

1.46

 Reyn

1.45

Utt

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.