INDEX

Explanations

specific phrases or patterns indicating opinions or conditions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/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.35.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

EnableWeb

-0.43

eschön

-0.36

efois

-0.36

orianCalendar

-0.36

 одни

-0.36

ViewFeatures

-0.35

stdbool

-0.35

PreAuthorize

-0.34

feof

-0.34

ceğine

-0.34

POSITIVE LOGITS

any

4.03

Any

3.09

Any

3.02

 qualquer

3.00

 cualquier

2.98

任何

2.92

any

2.92

 anything

2.89

ANY

2.88

 anyone

2.66

Activations Density 4.452%

specific phrases or patterns indicating opinions or conditions in various contexts

No Comments

No Known Activations