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

0:0.09

1:0.06

2:0.08

3:0.07

4:0.10

5:0.09

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 mascul

-1.49

Enable

-1.47

 Ruler

-1.47

RECT

-1.46

 Historical

-1.44

神

-1.41

ITIES

-1.41

 Municipal

-1.40

ORED

-1.40

 Authent

-1.39

POSITIVE LOGITS

hof

1.89

abal

1.78

achusetts

1.72

osures

1.66

pet

1.52

yrinth

1.51

agraph

1.49

aryl

1.47

selage

1.47

wagen

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.