INDEX

Explanations

requests for explanations or clarifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 volon

-0.50

botten

-0.45

 perfectly

-0.45

ceğini

-0.45

 commerciales

-0.45

 prendra

-0.44

 vectorielle

-0.44

FetchType

-0.43

 avvic

-0.43

 /*#__

-0.43

POSITIVE LOGITS

 defaultstate

0.81

 HttpNotFound

0.79

 InputDecoration

0.78

contentLoaded

0.77

 насељу

0.76

 AssemblyTitle

0.72

Autoritní

0.72

GEBURTSDATUM

0.71

WithIOException

0.70

 initComponents

0.70

Activations Density 0.228%

requests for explanations or clarifications

No Comments

No Known Activations