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

2:0.09

3:0.07

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 guessing

-1.63

lyn

-1.54

Sas

-1.47

 Ares

-1.45

IPS

-1.42

 boycot

-1.41

 assuming

-1.40

 Giles

-1.39

Yus

-1.38

 defending

-1.38

POSITIVE LOGITS

ebted

1.94

Limit

1.91

者

1.88

uph

1.88

Catalog

1.83

oğ

1.78

umbn

1.71

WIND

1.67

fml

1.67

ْ

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.