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

1:0.07

2:0.08

3:0.08

4:0.10

5:0.07

6:0.08

7:0.10

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Warfare

-1.64

 Pagan

-1.63

 Citizen

-1.60

 Greenpeace

-1.59

 Isis

-1.54

 Sigma

-1.54

 Fedora

-1.52

 Genie

-1.52

 Hacker

-1.50

 Armed

-1.48

POSITIVE LOGITS

rans

1.95

interstitial

1.92

escription

1.77

translation

1.77

QB

1.75

appropriately

1.74

�

1.70

adapt

1.64

ebted

1.63

execute

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.