INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.09

7:0.07

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

objects

-1.45

Yet

-1.40

Similarly

-1.36

acts

-1.31

MORE

-1.30

 Scientists

-1.29

 streaks

-1.28

 fossils

-1.23

 Objects

-1.22

 similarly

-1.21

POSITIVE LOGITS

chn

1.47

phasis

1.45

abase

1.45

rection

1.45

channelAvailability

1.41

 encount

1.40

ciating

1.39

 autos

1.36

eah

1.36

stall

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.