INDEX

Explanations

phrases related to evaluations and assessments of experiences or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

 disambiguazione

-0.53

nocześnie

-0.39

Notae

-0.39

Einzelnachweise

-0.37

帖最后由

-0.35

niająca

-0.35

 resourceCulture

-0.34

 EconPapers

-0.34

 referrerpolicy

-0.33

ExecuteReader

-0.32

POSITIVE LOGITS

 decent

1.70

 mediocre

1.50

 average

1.49

 okay

1.40

Decent

1.37

 Decent

1.35

ok

1.34

average

1.33

 decently

1.30

 acceptable

1.30

Activations Density 0.501%

phrases related to evaluations and assessments of experiences or services

No Comments

No Known Activations