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

5:0.07

6:0.09

7:0.08

8:0.08

9:0.07

10:0.09

11:0.06

Negative Logits

srf

-1.44

AF

-1.42

illary

-1.41

etheless

-1.40

ASA

-1.37

 manifests

-1.36

 practition

-1.34

 impacts

-1.34

 decay

-1.30

cms

-1.27

POSITIVE LOGITS

kefeller

1.54

olitics

1.52

zl

1.50

INTON

1.48

 Downing

1.44

undrum

1.42

wcsstore

1.40

udo

1.40

ername

1.38

ndum

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.