INDEX

Explanations

words and phrases related to secrecy and covert actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hdashline

-0.72

phazard

-0.65

CodeAttribute

-0.61

AnchorStyles

-0.58

stateProvider

-0.56

elemField

-0.56

原始内容存档于

-0.56

 Gubernur

-0.55

PyExc

-0.55

databind

-0.55

POSITIVE LOGITS

 secretly

1.31

 hidden

1.29

 secret

1.20

secret

1.07

 invisible

1.06

 Hidden

1.05

 quietly

1.01

 covert

1.00

 secreto

1.00

hidden

1.00

Activations Density 0.343%

words and phrases related to secrecy and covert actions

No Comments

No Known Activations