INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.09

1:0.10

2:0.07

3:0.07

4:0.08

5:0.06

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

regular

-2.92

spring

-2.53

Interested

-2.50

inguished

-2.47

owe

-2.36

nick

-2.32

PRE

-2.30

rit

-2.29

heimer

-2.19

Talk

-2.19

POSITIVE LOGITS

CTR

2.93

 BALL

2.34

 Sector

2.34

 Utility

2.28

 Ajax

2.23

 Stability

2.14

DonaldTrump

2.10

 sails

2.09

Dur

2.08

 utility

2.08

Activations Density 0.000%

No Known Activations

This feature has no known activations.