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

3:0.09

4:0.09

5:0.09

6:0.07

7:0.07

8:0.07

9:0.10

10:0.07

11:0.06

Negative Logits

anchester

-1.40

strength

-1.32

rule

-1.29

 absolute

-1.29

ngth

-1.29

 replay

-1.27

ailable

-1.23

lyak

-1.23

etheless

-1.22

 proportional

-1.20

POSITIVE LOGITS

Rah

1.42

neau

1.34

icer

1.23

 sponsoring

1.22

ullivan

1.14

 patrons

1.12

urdue

1.12

 Pricing

1.11

 ceremon

1.10

ician

1.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.