INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.05

1:0.04

2:0.16

3:0.10

4:0.08

5:0.03

6:0.08

7:0.11

8:0.03

9:0.04

10:0.11

11:0.10

Negative Logits

iversary

-1.54

 incrim

-1.53

olla

-1.48

 ransom

-1.46

 clues

-1.43

terday

-1.34

jong

-1.33

selage

-1.31

plet

-1.31

sov

-1.30

POSITIVE LOGITS

FX

1.46

 Frequency

1.43

 BELOW

1.31

oggles

1.29

黒

1.26

GY

1.25

 phosphorus

1.22

 Sodium

1.19

 Rage

1.18

 refreshing

1.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.