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

0:0.09

1:0.07

2:0.07

3:0.07

4:0.10

5:0.06

6:0.08

7:0.07

8:0.08

9:0.07

10:0.10

11:0.07

Negative Logits

amba

-1.64

tein

-1.44

 interf

-1.42

 upside

-1.42

tin

-1.36

otin

-1.34

han

-1.32

hin

-1.31

 selfie

-1.28

 subp

-1.28

POSITIVE LOGITS

 Soup

1.49

 Conquest

1.49

 Kers

1.48

 Ambro

1.47

 Towns

1.43

ONS

1.40

 Hutchinson

1.38

 Crunch

1.35

 Dispatch

1.33

UNCH

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.