INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.06

2:0.08

3:0.09

4:0.08

5:0.06

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 receipt

-1.57

 proportional

-1.45

ital

-1.39

Reviewer

-1.32

lement

-1.30

iliary

-1.29

POST

-1.27

ilings

-1.27

 legislatures

-1.27

External

-1.25

POSITIVE LOGITS

���

1.91

afort

1.63

��

1.56

ieri

1.55

acci

1.54

rower

1.42

 Oath

1.41

ertodd

1.39

eering

1.37

milo

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.