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

1:0.05

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.10

9:0.07

10:0.09

11:0.08

Negative Logits

 Genie

-1.75

llah

-1.75

isphere

-1.65

FTWARE

-1.62

 Emir

-1.50

 patrons

-1.48

Ward

-1.45

 shelves

-1.40

ESA

-1.39

IAS

-1.36

POSITIVE LOGITS

Cyn

1.44

 authored

1.42

heny

1.41

 aggreg

1.40

�

1.36

Ek

1.34

method

1.33

percent

1.32

 Percent

1.30

icing

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.