INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

1:0.10

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.07

11:0.08

Negative Logits

FU

-1.82

Ap

-1.80

Redd

-1.70

Always

-1.69

ritz

-1.64

Things

-1.61

Cra

-1.61

PLA

-1.60

KA

-1.59

 showc

-1.59

POSITIVE LOGITS

 ISIL

1.59

 Shiite

1.55

 Monte

1.52

BST

1.51

 Sachs

1.50

 Samson

1.49

 Marxist

1.48

 Samar

1.42

 Bearing

1.40

 Christians

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.