INDEX

Explanations

intensifiers and words expressing strong emotions or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 يتيمه

-0.66

 AssemblyProduct

-0.58

 Commencez

-0.56

Референце

-0.56

mored

-0.55

ционер

-0.52

 PhpStorm

-0.51

formik

-0.51

]='\

-0.51

 quoque

-0.51

POSITIVE LOGITS

ViewImports

0.76

 disappointed

0.65

 Cool

0.60

 cute

0.59

 COOL

0.59

 profesional

0.59

 funny

0.59

 disappointing

0.57

 cool

0.57

 impressed

0.57

Activations Density 0.161%

intensifiers and words expressing strong emotions or opinions

No Comments

No Known Activations