INDEX

Explanations

numerical data or references, particularly relating to dates and amounts

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

dates

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

évaluateur

-0.60



-0.41

 LEYENDO

-0.37

Personendaten

-0.36

Recipient

-0.36

 sideline

-0.36

covers

-0.34

VELAND

-0.34

 Kudos

-0.34

 العنوان

-0.34

POSITIVE LOGITS

IntoConstraints

0.54

UrlResolution

0.50

writeFieldEnd

0.47

SharedDtor

0.46

URLException

0.45

expandindo

0.44

OrBuilder

0.43

 bVar

0.43

reportWebVitals

0.43

 canst

0.42

Activations Density 0.047%

numerical data or references, particularly relating to dates and amounts

dates

No Comments

No Known Activations