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

0:0.09

1:0.08

2:0.06

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.07

9:0.09

10:0.09

11:0.10

Negative Logits

ensibly

-1.45

ohan

-1.44

ibly

-1.35

htaking

-1.32

®

-1.29

 GOODMAN

-1.29

ifully

-1.26

Cue

-1.26

gel

-1.25

yard

-1.22

POSITIVE LOGITS

���

1.47

��

1.44

juries

1.35

iHUD

1.32

ゴン

1.31

nings

1.26

arding

1.26

anda

1.26

EStream

1.25

zman

1.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.