INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.07

Negative Logits

 legislatures

-2.71

 SNAP

-2.51

 Common

-2.39

forestation

-2.37

DEM

-2.31

iberal

-2.30

bir

-2.28

 subsistence

-2.28

 Than

-2.25

Bir

-2.25

POSITIVE LOGITS

Ced

2.99

 Dome

2.71

 Rollins

2.62

 Cole

2.58

Ces

2.49

Doc

2.45

Jac

2.45

aq

2.40

Cole

2.40

 Floyd

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.