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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.10

Negative Logits

 compr

-1.43

arette

-1.43

edly

-1.32

MO

-1.27

ented

-1.27

VERTISEMENT

-1.26

apixel

-1.25

rily

-1.25

Recomm

-1.25

anto

-1.24

POSITIVE LOGITS

kj

1.53

░

1.30

wcs

1.30

 geography

1.23

ש

1.23

peak

1.22

abama

1.22

aos

1.21

 unpredict

1.20

qus

1.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.