INDEX

Explanations

instances of negation related to awareness or knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

assertIs

-0.41

 Distinguished

-0.38

 visit

-0.37

 document

-0.37

 seguida

-0.36

 report

-0.35

лтамалар

-0.35

 boletín

-0.35

//*[@

-0.35

encodeWith

-0.34

POSITIVE LOGITS

########.

0.63

Haven

0.62

cer

0.58

incredible

0.55

Cir

0.55

 ambi

0.54

⟬

0.54

 pinulongan

0.53

 incredible

0.52

IntoConstraints

0.51

Activations Density 0.225%

instances of negation related to awareness or knowledge

No Comments

No Known Activations

instances of negation related to awareness or knowledge

No Comments

No Known Activations