INDEX

Explanations

phrases related to projects and their descriptions or evaluations

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

1:0.01

2:0.06

3:0.19

4:0.18

5:0.02

6:0.06

7:0.14

8:0.04

9:0.04

10:0.08

11:0.11

Negative Logits

Rated

-1.76

�

-1.45

��

-1.39

 redes

-1.36

cember

-1.27

────

-1.27

Synopsis

-1.26

 face

-1.26

 destro

-1.26

Initialized

-1.24

POSITIVE LOGITS

 hairs

1.69

undle

1.31

aniel

1.31

govtrack

1.29

gallery

1.27

haps

1.24

entious

1.23

illac

1.23

 analogous

1.18

itual

1.18

Activations Density 0.006%

phrases related to projects and their descriptions or evaluations

No Comments

No Known Activations