INDEX

Explanations

references to database identifiers and peak values in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ApiException

-0.78

 disambiguazione

-0.77

hdashline

-0.71

 متعلقه

-0.71

']))

-0.70

 ddelweddau

-0.69

клопе

-0.66

❮

-0.64

…]

-0.63

CompleteListener

-0.63

POSITIVE LOGITS

ById

0.76

ByName

0.59

 positifs

0.55

 harian

0.54

唆

0.51

 commerciali

0.51

 faciles

0.51

DT

0.51

 giornal

0.50

 réserve

0.50

Activations Density 0.118%

references to database identifiers and peak values in scientific contexts

No Comments

No Known Activations