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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.07

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

ihil

-1.57

-1.49

uese

-1.44

asonic

-1.35

ormon

-1.33

shoot

-1.30

into

-1.25

hiro

-1.24

inding

-1.23

 motel

-1.23

POSITIVE LOGITS

 Marketable

1.65

 largeDownload

1.42

龍�

1.36

 deserve

1.31

 incentiv

1.30

reprene

1.30

Style

1.29

 Entreprene

1.28

 upfront

1.28

($

1.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.