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

IFrame

Link

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.07

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.10

Negative Logits

��

-1.46

erenn

-1.38

ETF

-1.38

oti

-1.37

 certs

-1.37

ostic

-1.35

uble

-1.35

arsity

-1.34

ochet

-1.31

ithe

-1.29

POSITIVE LOGITS

CGI

1.60

shows

1.56

LAND

1.50

ships

1.49

Sas

1.44

show

1.36

lihood

1.34

------

1.33

 secretive

1.32

 spoil

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.