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

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.06

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

Reviewed

-1.53

aired

-1.42

Lew

-1.41

Spoiler

-1.39

Upgrade

-1.39

Prev

-1.37

Lev

-1.37

Iv

-1.32

controlled

-1.31

Wiki

-1.29

POSITIVE LOGITS

ffield

1.67

acket

1.67

ixel

1.65

ierrez

1.61

acebook

1.60

ertodd

1.59

endas

1.50

chini

1.49

ophical

1.49

cox

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.