INDEX

Explanations

terms related to persuasion or convincing others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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



-0.88

Népesség

-0.80

GEBURTSDATUM

-0.79

InitVars

-0.77

 nargin

-0.76

 avoient

-0.73

 purpoſe

-0.72

 doInBackground

-0.71

 geburtstag

-0.71

 useNavigate

-0.71

POSITIVE LOGITS

Cle

1.64

Cle

1.50

cle

1.36

cle

1.35

CLE

1.30

CLE

1.28

 clearance

1.17

 Clearance

1.07

clearance

1.02

 cleared

0.94

Activations Density 0.137%

terms related to persuasion or convincing others

No Comments

No Known Activations