INDEX

Explanations

connections and references to numbers or quantifiable data in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ScopeManager

-0.42

ulipas

-0.42

oredCriteria

-0.40

Ой

-0.38

 Biôgrafia

-0.38

verwijspagina

-0.37

tagHelperRunner

-0.37

 pubb

-0.37

 unknownFields

-0.35

thalten

-0.35

POSITIVE LOGITS

 initComponents

0.67

mybatisplus

0.56

 Damit

0.49

 ready

0.47

 Somit

0.47

DebuggerStep

0.45

Ready

0.43

MathML

0.43

Damit

0.43

TabIndex

0.43

Activations Density 0.026%

connections and references to numbers or quantifiable data in a narrative context

No Comments

No Known Activations