INDEX

Explanations

phrases that imply perceptions of credibility and reputation, especially regarding how individuals are viewed in social contexts

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

appearance and perception analysis

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

MemoryWarning

-0.41

 azule

-0.38

 surla

-0.37

appBar

-0.36

pod

-0.35

denkmal

-0.35

SpringBootTest

-0.35

CloseOperation

-0.35

catraz

-0.34

 literal

-0.33

POSITIVE LOGITS

oa̍t

0.55

 initComponents

0.55

 BorderSide

0.51

StructEnd

0.50

yntaxException

0.47

featureID

0.46

$_"

0.46

⟬

0.45

Abitanti

0.45

被动

0.44

Activations Density 0.125%

phrases that imply perceptions of credibility and reputation, especially regarding how individuals are viewed in social contexts

appearance and perception analysis

No Comments

No Known Activations