INDEX

Explanations

occurrences of the word "for" and its variants in various contexts

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

Code snippets and programming-related terms

np_acts-logits-general · gemini-2.0-flash

prepositional phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 lisäksi

-0.51

 venido

-0.45

 minggu

-0.43

 creș

-0.42

raszamy

-0.42

 hvad

-0.42

 žá

-0.42

 thiệu

-0.40

 kuş

-0.40

 rumahnya

-0.40

POSITIVE LOGITS

ftagPool

0.77

 betweenstory

0.57

tvguidetime

0.56

MessageOf

0.56

endpush

0.56

 للمعارف

0.56

getAs

0.55

脚注の使い方

0.55

請繼續往下閱讀

0.55

 propOrder

0.55

Activations Density 0.180%

occurrences of the word "for" and its variants in various contexts

Code snippets and programming-related terms

prepositional phrases

No Comments

No Known Activations