INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.7.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

0:0.07

1:0.07

2:0.07

3:0.07

4:0.09

5:0.08

6:0.08

7:0.10

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 syndrome

-2.44

 Blueprint

-2.25

 scram

-2.02

 Syndrome

-2.00

Tam

-1.98

-1.95

isable

-1.91

 buffer

-1.89

-1.88

xit

-1.88

POSITIVE LOGITS

uscript

2.39

weet

2.28

arthed

2.26

artisan

2.25

achu

2.23

aughters

2.21

thal

2.10

eenth

2.09

�

2.05

 Indies

2.04

Activations Density 0.000%

No Known Activations

This feature has no known activations.