INDEX

Explanations

references to criminal activity or murder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 EconPapers

-0.84

 initComponents

-0.82

 referenties

-0.76

 intptr

-0.71

TypedDataSet

-0.71

 виправивши

-0.70

 &___

-0.70

 AssemblyCulture

-0.69

 HttpNotFound

-0.67

ManagedBean

-0.67

POSITIVE LOGITS

 homicide

0.61

 Homicide

0.50

 circonstances

0.44

 murder

0.42

 Wolfe

0.42

 circumstances

0.41

 homic

0.41

 autopsy

0.41

 précé

0.40

 julho

0.39

Activations Density 0.348%

references to criminal activity or murder

No Comments

No Known Activations