INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.05

2:0.10

3:0.09

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

iaz

-1.79

bably

-1.76

odynam

-1.72

urden

-1.70

atable

-1.67

 POLITICO

-1.64

isky

-1.50

ukes

-1.48

idding

-1.44

luaj

-1.44

POSITIVE LOGITS

 pale

1.51

ミ

1.45

 cerv

1.43

course

1.40

plain

1.39

 Purpose

1.38

 mathematics

1.37

purpose

1.34

 embry

1.30

 Eucl

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.