INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.09

2:0.07

3:0.08

4:0.05

5:0.07

6:0.08

7:0.06

8:0.09

9:0.09

10:0.10

11:0.05

Negative Logits

 grievance

-1.37

 Guam

-1.31

 hostilities

-1.30

 sparing

-1.28

 Labrador

-1.28

 euth

-1.26

 pardon

-1.24

 petition

-1.24

osterone

-1.23

 moderation

-1.20

POSITIVE LOGITS

 srfAttach

1.47

 SetFontSize

1.47

Appearances

1.44

oros

1.40

Example

1.39

rers

1.39

ufact

1.39

udeb

1.39

washer

1.35

ertodd

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.