INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.06

1:0.09

2:0.09

3:0.07

4:0.07

5:0.07

6:0.09

7:0.08

8:0.08

9:0.06

10:0.09

11:0.10

Negative Logits

TAG

-1.66

potion

-1.23

 dilig

-1.22

 Breath

-1.19

devices

-1.18

staking

-1.18

arta

-1.17

 Intelligence

-1.17

bart

-1.17

 Resistance

-1.15

POSITIVE LOGITS

tho

1.36

').

1.28

 Cheong

1.24

 havoc

1.23

 turnovers

1.22

 typo

1.17

 scratches

1.16

 Bridgewater

1.15

natureconservancy

1.15

?)

1.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.