INDEX

Explanations

phrases related to metrics and measurements

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_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

0:0.01

1:0.02

2:0.07

3:0.24

4:0.01

5:0.02

6:0.05

7:0.10

8:0.09

9:0.12

10:0.06

11:0.15

Negative Logits

bos

-1.17

sonian

-1.16

lers

-1.08

Alias

-1.06

FOX

-1.05

ppa

-0.99

INFO

-0.96

mate

-0.94

nis

-0.94

eus

-0.94

POSITIVE LOGITS

 footprint

1.19

 coma

1.15

erous

1.14

 seism

1.14

 backlog

1.13

 incidence

1.12

 mater

1.12

Quantity

1.07

 effectiveness

1.06

profits

1.05

Activations Density 0.023%

phrases related to metrics and measurements

No Comments

No Known Activations