INDEX

Explanations

words related to hidden or concealed elements

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

0:0.03

1:0.02

2:0.08

3:0.15

4:0.02

5:0.03

6:0.11

7:0.18

8:0.04

9:0.06

10:0.06

11:0.16

Negative Logits

Pwr

-1.43

apest

-1.31

ashtra

-1.31

iannopoulos

-1.23

hement

-1.18

ahime

-1.16

otaur

-1.14

ullivan

-1.13

 Bulg

-1.12

 Andrews

-1.10

POSITIVE LOGITS

 caches

1.26

 iceberg

1.25

 secret

1.21

 infiltr

1.19

 secrets

1.19

 fingerprints

1.15

 disgu

1.14

 obstruct

1.14

pires

1.10

 datasets

1.09

Activations Density 0.014%

words related to hidden or concealed elements

No Comments

No Known Activations