INDEX

Explanations

numerical data related to academic and assessment metrics

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

academic performance metrics

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

跆

-0.45

invalid

-0.44

 invalid

-0.42

+#+

-0.41

ьаж

-0.40

unteer

-0.40

↹

-0.40

GTCX

-0.39

quipe

-0.39

opardy

-0.39

POSITIVE LOGITS

期刊论文

0.43

 محفوظة

0.41

 Relaciones

0.37

 ifrån

0.36

ToProps

0.35

Referensi

0.34

ButterKnife

0.34

 regelmäßig

0.34

Carriera

0.33

PreAuthorize

0.33

Activations Density 0.070%

numerical data related to academic and assessment metrics

academic performance metrics

No Comments

No Known Activations