INDEX

Explanations

terms related to various types of alcoholic beverages and their consumption

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

alcoholic beverages

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

verwijspagina

-0.49

adpleegd

-0.46

✨:

-0.45

 praça

-0.43

JpaRepository

-0.43

 témoin

-0.43

 cherchés

-0.43

lesias

-0.41

hésite

-0.40

 jouets

-0.40

POSITIVE LOGITS

 surla

0.52

 Vodka

0.52

 vodka

0.51

 createSlice

0.49

Personensuche

0.48

 liqueur

0.47

出版年

0.46

 Distillery

0.44

tanleria

0.44

 liquor

0.43

Activations Density 0.035%

terms related to various types of alcoholic beverages and their consumption

alcoholic beverages

No Comments

No Known Activations