INDEX

Explanations

references to the presence or existence of something in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.02

1:0.00

2:0.15

3:0.06

4:0.20

5:0.03

6:0.18

7:0.10

8:0.04

9:0.03

10:0.07

11:0.06

Negative Logits

 dared

-1.43

 Commissioners

-1.27

ABE

-1.25

oka

-1.23

 accused

-1.23

 Rescue

-1.21

 Franch

-1.21

 Commissioner

-1.20

[*

-1.19

Reviewer

-1.17

POSITIVE LOGITS

 ferment

1.35

iosity

1.30

Cause

1.28

LESS

1.24

govtrack

1.23

ongh

1.23

ocamp

1.22

 obscurity

1.22

matter

1.19

atable

1.18

Activations Density 0.002%

references to the presence or existence of something in various contexts

No Comments

No Known Activations