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

0:0.07

1:0.10

2:0.07

3:0.10

4:0.04

5:0.07

6:0.07

7:0.07

8:0.08

9:0.10

10:0.11

11:0.05

Negative Logits

___

-1.38

sheets

-1.38

govtrack

-1.19

 breeze

-1.17

mol

-1.16

talk

-1.16

 dumps

-1.15

Iv

-1.14

acet

-1.14

ρ

-1.12

POSITIVE LOGITS

 Chess

1.45

 CARD

1.35

 Frontier

1.31

Bar

1.29

 Card

1.29

rongh

1.25

 Format

1.25

tyard

1.18

 Gate

1.17

ainment

1.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.