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

0:0.08

1:0.06

2:0.09

3:0.07

4:0.08

5:0.08

6:0.07

7:0.10

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

 seizures

-1.60

 Beng

-1.45

alien

-1.45

!'

-1.44

 hysteria

-1.41

 impunity

-1.40

 seizure

-1.38

 delusions

-1.37

 Gems

-1.37

Ep

-1.36

POSITIVE LOGITS

ascript

1.88

ificial

1.72

eto

1.72

ginx

1.65

razil

1.59

��

1.58

ˈ

1.58

 shortened

1.57

uyomi

1.56

icipated

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.