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

1:0.09

2:0.09

3:0.07

4:0.06

5:0.08

6:0.08

7:0.09

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

 incapac

-2.28

 disgu

-2.27

onym

-2.27

 summons

-2.17

 counterfe

-2.10

 masked

-2.06

 fools

-2.06

 banging

-2.00

iatus

-2.00

POSITIVE LOGITS

DF

2.18

^{

2.12

inelli

2.10

�

2.07

AFTA

2.06

 Trib

2.06

Georgia

2.06

swick

2.04

UST

2.01

inion

1.98

Activations Density 0.000%

No Known Activations

This feature has no known activations.