INDEX

Explanations

mentions of specific names or identifiers, possibly related to people or entities within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 récord

-0.46

 attendu

-0.42

 serons

-0.42

 Vaters

-0.40

лтамалар

-0.40

 Gegenteil

-0.40

 للمعارف

-0.39

 devenus

-0.38

 Gebrauch

-0.38

 Handeln

-0.38

POSITIVE LOGITS

########.

0.65

enumii

0.52

requireNonNull

0.51

(!__

0.51

 AssemblyCompany

0.49

+#+

0.49

Sg

0.48

$__

0.47

 AppCompatTheme

0.47

="@+

0.46

Activations Density 0.018%

mentions of specific names or identifiers, possibly related to people or entities within a context

No Comments

No Known Activations